| Understanding and Steering Llama 3 with Sparse Autoencoders | Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 | 10.48550/arxiv.2408.05147 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | SAE-derived indicators provide a sharp lens into per-sample distribution shift w | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | project-gutenberg-poetry-corpus | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Sparse Crosscoders for Cross-Layer Features and Model Diffing | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Towards monosemanticity: Decomposing language models with dictionary learning | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Prisma: An Open Source Toolkit | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Toy Models of Superposition | 10.48550/arxiv.2209.10652 | active | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | UNDERSTAND-ING DEEP LEARNING REQUIRES RE-THINKING GENERALIZATION | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Pattern recognition and machine learning Information science and statistics | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Announcing open-source saes for llama 3.3 70b and llama 3.1 8b | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Language Models are Unsupervised Multitask Learners | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Dataset Shift in Machine Learning | 10.7551/mitpress/978026217 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neura | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on L | 10.21437/interspeech.2018- | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | SQuAD: 100,000+ Questions for Machine Comprehension of Text | 10.18653/v1/d16-1264 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Convergent Learning: Do different neural networks learn the same representations | 10.48550/arxiv.1511.07543 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Deep Anomaly Detection with Outlier Exposure | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversa | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Exploring the Limits of Weakly Supervised Pretraining | 10.1007/978-3-030-01216-8_ | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Invariant Risk Minimization | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Do ImageNet Classifiers Generalize to ImageNet? | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Scaling Laws for Neural Language Models | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Language Models are Few-Shot Learners | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | On Faithfulness and Factuality in Abstractive Summarization | 10.18653/v1/2020.acl-main. | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Energy-based Out-of-distribution Detection | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Measuring Massive Multitask Language Understanding | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Survey of Hallucination in Natural Language Generation | 10.1145/3571730 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Learning Transferable Visual Models From Natural Language Supervision | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Training Compute-Optimal Large Language Models | 10.52202/068431-2176 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Holistic Evaluation of Language Models | 10.1111/nyas.15007 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | TinyStories: How Small Can Language Models Be and Still Speak Coherent English? | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Emergent Abilities of Large Language Models | 10.48550/arxiv.2206.07682 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Steering language models with activation engineering | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Sparse autoencoders find highly interpretable features in language models | 10.48550/arxiv.2309.08600 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Jailbroken: How does LLM safety training fail? | 10.48550/arxiv.2307.02483 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Universal and Transferable Adversarial Attacks on Aligned Language Models | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | LMSYS-Chat-1M: A large-scale real-world LLM conversation dataset | 10.48550/arxiv.2309.11998 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | The linear representation hypothesis and the geometry of large language models | 10.48550/arxiv.2311.03658 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | A StrongREJECT for Empty Jailbreaks | 10.48550/arxiv.2402.10260 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Not all language model features are one-dimensionally linear | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | LLM Task Interference: An Initial Study on the Impact of Task-Switch in Conversa | 10.48550/arxiv.2402.18216 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey | 10.48550/arxiv.2403.14608 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Jailbreak Attacks and Defenses Against Large Language Models: A Survey | 10.48550/arxiv.2407.04295 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | OR-Bench: An Over-Refusal Benchmark for Large Language Models | 10.48550/arxiv.2405.20947 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Langu | 10.48550/arxiv.2406.18510 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Quantifying Feature Space Universality Across Large Language Models via Sparse A | — | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Decomposing The Dark Matter of Sparse Autoencoders | 10.48550/arxiv.2410.14670 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Reasoning Robustness of LLMs to Adversarial Typographical Errors | 10.18653/v1/2024.emnlp-mai | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark | 10.48550/arxiv.2412.15194 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Steering Language Model Refusal with Sparse Autoencoders | 10.48550/arxiv.2411.11296 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Sparse Autoencoders Trained on the Same Data Learn Different Features | 10.48550/arxiv.2501.16615 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Which of These Best Describes Multiple Choice Evaluation with LLMs? A) Forced B) | 10.48550/arxiv.2502.14127 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Sparse Autoencoders Do Not Find Canonical Units of Analysis | 10.48550/arxiv.2502.04878 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | The origins of representation manifolds in large language models | 10.48550/arxiv.2505.18235 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Steering CLIP's vision transformer with sparse autoencoders | 10.48550/arxiv.2504.08729 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers | 10.48550/arxiv.2509.06938 | referenced-only | s2-reference-walk |
| Understanding and Steering Llama 3 with Sparse Autoencoders | Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet | — | active | s2-reference-walk |
| Stochastic Parameter Decomposition | Sparse Crosscoders for Cross-Layer Features and Model Diffing | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Skeletonization: A Technique for Trimming the Fat from a Network via Relevance A | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Causal scrubbing: a method for rigorously testing interpretability hypotheses | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Algebraic geometry and statistical learning theory | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Tanh penalty in dictionary learning | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Towards monosemanticity: Decomposing language models with dictionary learning | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Taking features out of superposition with sparse autoencoders | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | The Quest for the Right Mediator: A History, Survey, and Theoretical Grounding o | 10.48550/arxiv.2408.01416 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Addressing feature suppression in saes | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Investigating Gender Bias in Language Models Using Causal Mediation Analysis | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | AUTO-ENCODING VARIATIONAL BAYES | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Axiomatic Attribution for Deep Networks | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Counterfactuals | 10.1007/bf02123381 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Deep Inside Convolutional Networks: Visualising Image Classification Models and | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Sanity Checks for Saliency Maps | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Conceptual challenges for interpretable machine learning | 10.1007/s11229-022-03485-5 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Decoupled Weight Decay Regularization | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Interpretable explanations of black boxes by meaningful perturbation | 10.1109/iccv.2017.371 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Transformer visualization via dictionary learning: contextualized embedding as a | 10.18653/v1/2021.deelio-1. | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Low-Complexity Probing via Finding Subnetworks | 10.18653/v1/2021.naacl-mai | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Interpretability in the Wild: a Circuit for Indirect Object Identification in GP | 10.48550/arxiv.2211.00593 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Can Subnetwork Structure be the Key to Out-of-Distribution Generalization? | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Causal abstractions of neural networks | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Finding Alignments Between Interpretable Causal Variables and Distributed Neural | 10.48550/arxiv.2303.02536 | active | s2-reference-walk |
| Stochastic Parameter Decomposition | The Hydra Effect: Emergent Self-repair in Language Model Computations | 10.48550/arxiv.2307.15771 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Towards Automated Circuit Discovery for Mechanistic Interpretability | 10.48550/arxiv.2304.14997 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Attribution Patching Outperforms Automated Circuit Discovery | 10.48550/arxiv.2310.10348 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Uncovering Model Processing Strategies with Non-Negative Per-Example Fisher Fact | — | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Sparse autoencoders find highly interpretable features in language models | 10.48550/arxiv.2309.08600 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Missed Causes and Ambiguous Effects: Counterfactuals Pose Challenges for Interpr | 10.48550/arxiv.2407.04690 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | AtP*: An efficient and scalable method for localizing LLM behaviour to component | 10.48550/arxiv.2403.00745 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in | 10.48550/arxiv.2403.19647 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoenc | 10.48550/arxiv.2409.14507 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Mathematical Models of Computation in Superposition | 10.48550/arxiv.2408.05451 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Sparse Autoencoders Do Not Find Canonical Units of Analysis | 10.48550/arxiv.2502.04878 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Interpretability in Parameter Space: Minimizing Mechanistic Description Length w | 10.48550/arxiv.2501.14926 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Differentiation and Specialization of Attention Heads via the Refined Local Lear | 10.48550/arxiv.2410.02984 | referenced-only | s2-reference-walk |
| Stochastic Parameter Decomposition | Identifying Sparsely Active Circuits Through Local Loss Landscape Decomposition | 10.48550/arxiv.2504.00194 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet | — | active | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Co | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Towards monosemanticity: Decomposing language models with dictionary learning | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Intriguing properties of neural networks | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Do Perceptually Aligned Gradients Imply Adversarial Robustness? | 10.48550/arxiv.2207.11378 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Explaining and Harnessing Adversarial Examples | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | ImageNet Large Scale Visual Recognition Challenge | 10.1007/s11263-015-0816-y | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial examples in the physical world | 10.1201/9781351251389-8 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Towards Evaluating the Robustness of Neural Networks | 10.1109/sp.2017.49 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks | 10.1109/cvpr.2016.282 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Universal Adversarial Perturbations | 10.1109/cvpr.2017.17 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Towards Deep Learning Models Resistant to Adversarial Attacks | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Delving into Transferable Adversarial Examples and Black-box Attacks | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Certified Robustness to Adversarial Examples with Differential Privacy | 10.1109/sp.2019.00044 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial Spheres | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Understanding and Enhancing the Transferability of Adversarial Examples | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Are adversarial examples inevitable? | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarially Robust Generalization Requires More Data | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Robustness May Be at Odds with Accuracy | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and P | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | On the Geometry of Adversarial Examples | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | On the Effectiveness of Interval Bound Propagation for Training Verifiably Robus | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks fro | 10.1609/aaai.v33i01.330145 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | On the Effectiveness of Low Frequency Perturbations | 10.24963/ijcai.2019/470 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | An Information-Theoretic Explanation for the Adversarial Fragility of AI Classif | 10.1109/isit.2019.8849757 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Theoretically Principled Trade-off between Robustness and Accuracy | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial Robustness vs. Model Compression, or Both? | 10.1109/iccv.2019.00020 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Certified Adversarial Robustness via Randomized Smoothing | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Model Compression with Adversarial Robustness: A Unified Optimization Framework | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial Examples Are Not Bugs, They Are Features | 10.48550/arxiv.1905.02175 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Empirically Measuring Concentration: Fundamental Limits on Intrinsic Robustness | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial Training for Free! | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Unlabeled Data Improves Adversarial Robustness | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial Robustness as a Prior for Learned Representations | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Understanding and Mitigating the Tradeoff Between Robustness and Accuracy | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Precise Tradeoffs in Adversarial Training for Linear Regression | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Overfitting in adversarially robust deep learning | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Reliable evaluation of adversarial robustness with an ensemble of diverse parame | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Do Adversarially Robust ImageNet Models Transfer Better? | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Derivation of Information-Theoretically Optimal Adversarial Attacks with Applica | 10.1109/ieeeconf60004.2024 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Adversarial Robustness through Disentangled Representations | 10.1609/aaai.v35i4.16424 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | The Dimpled Manifold Model of Adversarial Examples in Machine Learning | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Toy Models of Superposition | 10.48550/arxiv.2209.10652 | active | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Understanding Adversarial Robustness Against On-manifold Adversarial Examples | 10.48550/arxiv.2210.00430 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifol | 10.48550/arxiv.2305.19101 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Sparse autoencoders find highly interpretable features in language models | 10.48550/arxiv.2309.08600 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | A High Dimensional Statistical Model for Adversarial Training: Geometry and Trad | — | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | Exploring the Interplay of Interpretability and Robustness in Deep Neural Networ | 10.1109/icipcw64161.2024.1 | referenced-only | s2-reference-walk |
| Adversarial Examples Are Not Bugs, They Are Superposition | On the Complexity of Neural Computation in Superposition | 10.48550/arxiv.2409.15318 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | What is a linear representation? What is a multidimensional feature? | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Towards monosemanticity: Decomposing language models with dictionary learning | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Up-date on how we train saes | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | The dark matter of neural networks? Transformer Circuits Thread | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Sparse Crosscoders for Cross-Layer Features and Model Diffing | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Toy Models of Superposition | 10.48550/arxiv.2209.10652 | active | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Robustly identifying concepts introduced during chat fine-tuning using crosscode | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Training Compute-Optimal Large Language Models | 10.52202/068431-2176 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Scaling Laws for Neural Language Models | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Sparse autoencoders find highly interpretable features in language models | 10.48550/arxiv.2309.08600 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Not all language model features are one-dimensionally linear | — | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | The Quantization Model of Neural Scaling | 10.48550/arxiv.2303.13506 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencode | 10.48550/arxiv.2407.14435 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Scaling and evaluating sparse autoencoders | 10.48550/arxiv.2406.04093 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Transcoders Find Interpretable LLM Feature Circuits | 10.48550/arxiv.2406.11944 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Recurrent neural networks learn to store and generate sequences using non-linear | 10.48550/arxiv.2408.10920 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoenc | 10.48550/arxiv.2409.14507 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 | 10.48550/arxiv.2408.05147 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Batchtopk sparse autoencoders | 10.48550/arxiv.2412.06410 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Group Crosscoders for Mechanistic Analysis of Symmetry | 10.48550/arxiv.2410.24184 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Decomposing The Dark Matter of Sparse Autoencoders | 10.48550/arxiv.2410.14670 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geom | 10.48550/arxiv.2503.01822 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Neural Scaling Laws Rooted in the Data Distribution | 10.48550/arxiv.2412.07942 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Archetypal sae: Adaptive and stable dictionary learning for concept extraction i | 10.48550/arxiv.2502.12892 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures | 10.48550/arxiv.2506.01197 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | From flat to hierarchical: Extracting sparse representations with matching pursu | 10.48550/arxiv.2506.03093 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | The origins of representation manifolds in large language models | 10.48550/arxiv.2505.18235 | referenced-only | s2-reference-walk |
| Understanding sparse autoencoder scaling in the presence of | Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet | — | active | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Symbols Among the Neurons: Details of a Connectionist Inference Architecture | — | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Recency and primacy in persuasion as a function of the timing of speeches and me | 10.1037/h0049330 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Investigating Gender Bias in Language Models Using Causal Mediation Analysis | — | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Tensor Product Variable Binding and the Representation of Symbolic Structures in | 10.7551/mitpress/2102.003. | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Language Models are Few-Shot Learners | — | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Connectionism and cognitive architecture: a critical analysis. | 10.1016/0010-0277(88)90031 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Neural natural language inference models partially embed theories of lexical ent | 10.18653/v1/2020.blackboxn | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Memory: A Contribution to Experimental Psychology | 10.5214/ans.0972.7531.2004 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Causal abstraction: A theoretical foundation for mechanistic interpretability | — | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Causal analysis of syntactic agreement mechanisms in neural language models | 10.18653/v1/2021.acl-long. | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Causal abstractions of neural networks | — | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Dissecting recall of factual associations in auto-regressive language models | 10.48550/arxiv.2304.14767 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Lost in the Middle: How Language Models Use Long Contexts | 10.1162/tacl_a_00638 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Discovering variable binding circuitry with desiderata | 10.48550/arxiv.2307.03637 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance | 10.48550/arxiv.2402.14848 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Aspects of human memory and Large Language Models | 10.48550/arxiv.2311.03839 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | How do language models bind entities in context? | 10.48550/arxiv.2310.17191 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Representational Analysis of Binding in Language Models | 10.18653/v1/2024.emnlp-mai | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Monitoring Latent World States in Language Models with Propositional Probes | 10.48550/arxiv.2406.19501 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking | 10.48550/arxiv.2402.14811 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | How Do Transformers Learn Variable Binding in Symbolic Programs? | 10.48550/arxiv.2505.20896 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Combining Causal Models for More Accurate Abstractions of Neural Networks | 10.48550/arxiv.2503.11429 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | Language Models use Lookbacks to Track Beliefs | 10.48550/arxiv.2505.14685 | referenced-only | s2-reference-walk |
| Mixing Mechanisms: How Language Models Retrieve Bound Entiti | How causal abstraction underpins computational explanation | 10.48550/arxiv.2508.11214 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Towards monosemanticity: Decomposing language models with dictionary learning | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet | — | active | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | log p ( x | c ) p ( x | c ′ ) = log p ( x | c ) − log p ( x | c ′ ) ≈ γN − α ( − | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Gem-ini: a family of highly capable multimodal models | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Activation addition: Steering language models without optimization | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Vision: A computational investigation into the human representation and processi | 10.1016/0022-2496(83)90030 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Many-shot Jailbreaking | 10.52202/079017-4121 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Measuring the crowd within: Probabilistic representations within individuals | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | A Rational Analysis of Rule-Based Concept Learning | 10.1080/03640210701802071 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | How to grow a mind: statistics, structure, and abstraction | 10.1126/science.1192788 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Efficient Estimation of Word Representations in Vector Space | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | When is a crowd wise? | 10.1037/dec0000004 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | A Latent Variable Model Approach to PMI-based Word Embeddings | 10.1162/tacl_a_00106 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Good debt or bad debt: Detecting semantic orientations in economic texts | 10.1002/asi.23062 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | BERT Rediscovers the Classical NLP Pipeline | 10.18653/v1/p19-1452 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Bayesian Models of Conceptual Development: Learning as Building Models of the Wo | 10.31234/osf.io/aq3rp | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Language Models are Few-Shot Learners | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Scaling Laws for Neural Language Models | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Causal abstractions of neural networks | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Probing classifiers: Promises, shortcomings, and advances | 10.1162/coli_a_00422 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natu | 10.1145/3560815 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Chain of Thought Prompting Elicits Reasoning in Large Language Models | 10.52202/068431-1800 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | An Explanation of In-context Learning as Implicit Bayesian Inference | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Rethinking the Role of Demonstrations: What Makes In-Context Learning Work? | 10.18653/v1/2022.emnlp-mai | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Training a Helpful and Harmless Assistant with Reinforcement Learning from Human | 10.48550/arxiv.2204.05862 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | CAT'S THEORY: Empirical Validation and Architectural Applications Cross-Architec | 10.48550/arxiv.2212.08073 | active | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Transformers generalize differently from information stored in context vs in wei | 10.48550/arxiv.2210.05675 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Causal abstraction: A theoretical foundation for mechanistic interpretability | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Discovering language model behaviors with model-written evaluations | 10.48550/arxiv.2212.09251 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Transformers learn in-context by gradient descent | 10.48550/arxiv.2212.07677 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Sparks of Artificial General Intelligence: Early experiments with GPT-4 | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT | 10.64346/plop2023p05 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameter | 10.48550/arxiv.2305.19420 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Pretraining task diversity and the emergence of non-Bayesian in-context learning | 10.48550/arxiv.2306.15063 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Inference-time intervention: eliciting truthful answers from a language model | 10.52202/075280-1797 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | In-context learning dynamics with random binary sequences | 10.48550/arxiv.2310.17639 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | The Geometry of Truth: Emergent Linear Structure in Large Language Model Represe | 10.48550/arxiv.2310.06824 | active | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | A Survey on Evaluation of Large Language Models | 10.1145/3641289 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Steering Llama 2 via Contrastive Activation Addition | 10.48550/arxiv.2312.06681 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | The linear representation hypothesis and the geometry of large language models | 10.48550/arxiv.2311.03658 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | The mechanistic basis of data dependence and abrupt learning in an in-context cl | 10.48550/arxiv.2312.03002 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | A Systematic Survey of Prompt Engineering in Large Language Models: Techniques a | 10.48550/arxiv.2402.07927 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | In-Context Language Learning: Architectures and Algorithms | 10.48550/arxiv.2401.12973 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | LLMs learn governing principles of dynamical systems, revealing an in-context ne | 10.48550/arxiv.2402.00795 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Language Models Represent Beliefs of Self and Others | 10.48550/arxiv.2402.18496 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Foundational Challenges in Assuring Alignment and Safety of Large Language Model | 10.48550/arxiv.2404.09932 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | The Geometry of Categorical and Hierarchical Concepts in Large Language Models | 10.48550/arxiv.2406.01506 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Many-Shot In-Context Learning | 10.48550/arxiv.2404.11018 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Designing a Dashboard for Transparency and Control of Conversational AI | 10.48550/arxiv.2406.07882 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework | 10.48550/arxiv.2408.12664 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | The llama 3 herd of models | 10.48550/arxiv.2407.21783 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Refusal in language models is mediated by a single direction | 10.48550/arxiv.2406.11717 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Exploring the Personality Traits of LLMs through Latent Features Steering | — | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Sparse Autoencoders Reveal Temporal Difference Learning in Large Language Models | 10.48550/arxiv.2410.01280 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | In-Context Learning Enables Robot Action Prediction in LLMs | 10.1109/icra55743.2025.111 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Bayesian scaling laws for in-context learning | 10.48550/arxiv.2410.16531 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Towards Reliable Evaluation of Behavior Steering Interventions in LLMs | 10.48550/arxiv.2410.17245 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Competition Dynamics Shape Algorithmic Phases of In-Context Learning | 10.48550/arxiv.2412.01003 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Differential learning kinetics govern the transition from memorization to genera | 10.48550/arxiv.2412.00104 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | The broader spectrum of in-context learning | 10.48550/arxiv.2412.03782 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Iclr: In-context learning of representations | 10.48550/arxiv.2501.00070 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | In-Context Learning Strategies Emerge Rationally | 10.48550/arxiv.2506.17859 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Persona Vectors: Monitoring and Controlling Character Traits in Language Models | 10.48550/arxiv.2507.21509 | active | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Are language models aware of the road not taken? Token-level uncertainty and hid | 10.48550/arxiv.2511.04527 | referenced-only | s2-reference-walk |
| Belief Dynamics Reveal the Dual Nature of In-Context Learnin | Emergence of Linear Truth Encodings in Language Models | 10.48550/arxiv.2510.15804 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | On memorization and privacy risks of sharpness aware minimization | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Flat Minima | 10.1162/neco.1997.9.1.1 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Fact finding: How to think about interpreting memorisation (post 4) — AI | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Optimal Brain Damage | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Understanding Memorization in Generative Models via Sharpness in Probability Lan | 10.48550/arxiv.2412.04140 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | ImageNet Large Scale Visual Recognition Challenge | 10.1007/s11263-015-0816-y | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Optimal Brain Surgeon and general network pruning | 10.1109/icnn.1993.298572 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Optimizing Neural Networks with Kronecker-factored Approximate Curvature | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Membership Inference Attacks Against Machine Learning Models | 10.1109/sp.2017.41 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Sharpness-Aware Minimization for Efficiently Improving Generalization | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | An Investigation into Neural Net Optimization via Hessian Eigenvalue Density | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Netw | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Understanding deep learning requires rethinking generalization | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Knowledge Neurons in Pretrained Transformers | 10.18653/v1/2022.acl-long. | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Transformer feed-forward layers are key-value memories | 10.18653/v1/2021.emnlp-mai | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Does Localization Inform Editing? Surprising Differences in Causality-Based Loca | 10.48550/arxiv.2301.04213 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Locating and editing factual associations in GPT | 10.52202/068431-1262 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Quantifying Memorization Across Neural Language Models | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Language Models Implement Simple Word2Vec-style Vector Arithmetic | 10.48550/arxiv.2305.16130 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Memorization Through the Lens of Curvature of Loss Function Around Samples | 10.48550/arxiv.2307.05831 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Can Neural Network Memorization Be Localized? | 10.48550/arxiv.2307.09542 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Embers of Autoregression: Understanding Large Language Models Through the Proble | 10.48550/arxiv.2309.13638 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Linearity of Relation Decoding in Transformer Language Models | 10.48550/arxiv.2308.09124 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Compressing LLMs: The Truth is Rarely Pure and Never Simple | 10.48550/arxiv.2310.01382 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two | 10.48550/arxiv.2311.09060 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Copyright Violations and Large Language Models | 10.48550/arxiv.2310.13771 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | The Truth is in There: Improving Reasoning in Language Models with Layer-Selecti | 10.48550/arxiv.2312.13558 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection | 10.48550/arxiv.2403.03507 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Unveiling Privacy, Memorization, and Input Curvature Links | 10.48550/arxiv.2402.18726 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Localizing Paragraph Memorization in Language Models | 10.48550/arxiv.2403.19851 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Using Degeneracy in the Loss Landscape for Mechanistic Interpretability | 10.48550/arxiv.2405.10927 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | OLMES: A Standard for Language Model Evaluations | 10.48550/arxiv.2406.08446 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Demystifying Verbatim Memorization in Large Language Models | 10.48550/arxiv.2407.17817 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Arithmetic without algorithms: language models solve math with a bag of heuristi | 10.48550/arxiv.2410.21272 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Approaching Deep Learning through the Spectral Dynamics of Weights | 10.48550/arxiv.2408.11804 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Mitigating Memorization In Language Models | 10.48550/arxiv.2410.02159 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Differential learning kinetics govern the transition from memorization to genera | 10.48550/arxiv.2412.00104 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Measuring Non-Adversarial Reproduction of Training Data in Large Language Models | 10.48550/arxiv.2411.10242 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | OLMo 2 furious | 10.48550/arxiv.2501.00656 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Language models use trigonometry to do addition | 10.48550/arxiv.2502.00873 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Analyzing Memorization in Large Language Models through the Lens of Model Attrib | 10.48550/arxiv.2501.05078 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Structural Inference: Interpreting Small Language Models with Susceptibilities | — | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Precise In-Parameter Concept Erasure in Large Language Models | 10.48550/arxiv.2505.22586 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | On linear representations and pretraining data frequency in language models | 10.48550/arxiv.2504.12459 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | How much do language models memorize? | 10.48550/arxiv.2505.24832 | referenced-only | s2-reference-walk |
| From Memorization to Reasoning in the Spectrum of Loss Curva | Stochastic Parameter Decomposition | 10.48550/arxiv.2506.20790 | active | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Neural manifold geometry encodes feature fields | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Deploying interpretability to production with rakuten: Sae probes for pii detect | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Political bias dataset: A synthetic dataset for bias detection and reduction | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Receptive fields, binocular interaction and functional architecture in the cat's | 10.1113/jphysiol.1962.sp00 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A Global Geometric Framework for Nonlinear Dimensionality Reduction | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Towards monosemanticity: Decomposing language models with dictionary learning | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Covariance selection | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Global Versus Local Methods in Nonlinear Dimensionality Reduction | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Spatial Interaction and the Statistical Analysis of Lattice Systems | 10.1111/j.2517-6161.1974.t | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Optimally sparse representation in general (nonorthogonal) dictionaries via l mi | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Narrow Versus Wide Tuning Curves: What's Best for a Population Code? | 10.1162/089976699300016818 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Monology | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Finding the tree of life in evo 2 | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Diffusion maps | 10.1016/j.acha.2006.04.006 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | linear subspace clustering: a comparative study of nonlinear manifold clustering | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Using interpretability to identify a novel class of biomarkers for alzheimer’s d | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Receptive fields and functional architecture of monkey striate cortex | 10.1113/jphysiol.1968.sp00 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Information Theory and Statistical Mechanics | 10.1103/physrev.106.620 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Beitrag zur Theorie des Ferromagnetismus | 10.1007/bf02980577 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The hippocampus as a spatial map. Preliminary evidence from unit activity in the | 10.1016/0006-8993(71)90358 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Information processing with population codes | 10.1038/35039062 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Neuronal population coding of movement direction. | 10.1126/science.3749885 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Sparse coding with an overcomplete basis set: a strategy employed by V1? | 10.1016/s0042-6989(97)0016 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Emergence of simple-cell receptive field properties by learning a sparse code fo | 10.1038/381607a0 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Nonlinear dimensionality reduction by locally linear embedding. | 10.1126/science.290.5500.2 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering | 10.7551/mitpress/1120.003. | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | GRASSMANNIAN FRAMES WITH APPLICATIONS TO CODING AND COMMUNICATION | 10.1016/s1063-5203(03)0002 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data | 10.1073/pnas.1031596100 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Greed is good: algorithmic results for sparse approximation | 10.1109/tit.2004.834793 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Principal manifolds and nonlinear dimensionality reduction via tangent space ali | 10.1007/s11741-004-0051-1 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Just relax: convex programming methods for identifying sparse signals in noise | 10.1109/tit.2005.864420 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Weak pairwise correlations imply strongly correlated network states in a neural | 10.1038/nature04701 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Tuning Curves, Neuronal Variability, and Sensory Coding | 10.1371/journal.pbio.00400 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | High-dimensional graphs and variable selection with the Lasso | 10.1214/009053606000000281 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Sparse inverse covariance estimation with the graphical lasso. | 10.1093/biostatistics/kxm0 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Finding the Homology of Submanifolds with High Confidence from Random Samples | 10.1007/s00454-008-9053-2 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Neuronal couplings between retinal ganglion cells inferred by efficient inverse | 10.1073/pnas.0906705106 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Graphical Models, Exponential Families, and Variational Inference | 10.1561/2200000001 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Nonlinear Learning using Local Coordinate Coding | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Locality-constrained Linear Coding for image classification | 10.1109/cvpr.2010.5540018 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Robust Subspace Segmentation by Low-Rank Representation | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Sparse Manifold Clustering and Embedding | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Robust Recovery of Subspace Structures by Low-Rank Representation | 10.1109/tpami.2012.88 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Sparse Subspace Clustering: Algorithm, Theory, and Applications | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Robust Subspace Clustering | 10.1214/13-aos1199 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Kernel sparse subspace clustering | 10.1109/icip.2014.7025576 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Locally Linear Landmarks for Large-Scale Manifold Learning | 10.1007/978-3-642-40994-3_ | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Efficient Estimation of Word Representations in Vector Space | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | On the Number of Linear Regions of Deep Neural Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit | 10.1109/cvpr.2016.425 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A new method for constructing networks from binary data | 10.1038/srep05918 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Representation Benefits of Deep Feedforward Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Linear algebraic structure of word senses, with applications to polysemy | 10.1162/tacl_a_00034 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | On the Expressive Power of Deep Neural Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | An Empirical Analysis of Formality in Online Communication | 10.1162/tacl_a_00083 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Barlow versus Hebb: When is it time to abandon the notion of feature detectors a | 10.1016/j.neulet.2017.04.0 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Noisy Subspace Clustering via Matching Pursuits | 10.1109/tit.2018.2812824 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Cl | 10.1109/tip.2017.2691557 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Classification and Geometry of General Perceptual Manifolds | 10.1103/physrevx.8.031003 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Clos | 10.1145/3219819.3220063 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Bounding and Counting Linear Regions of Deep Neural Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Deep Subspace Clustering Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Sparse Manifold Transform | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Mad Max: Affine Spline Insights Into Deep Learning | 10.1109/jproc.2020.3042100 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A Spline Theory of Deep Learning | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Empirical Studies on the Properties of Linear Regions in Deep Neural Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Separability and geometry of object manifolds in deep neural networks | 10.1038/s41467-020-14578-5 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Complexity of Linear Regions in Deep Networks | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Graphical Models | 10.5860/choice.34-5144 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A Critique of Self-Expressive Deep Subspace Clustering | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Pile: An 800GB Dataset of Diverse Text for Language Modeling | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Probing classifiers: Promises, shortcomings, and advances | 10.1162/coli_a_00422 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Neural population geometry: An approach for understanding biological and artific | 10.1016/j.conb.2021.10.010 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Toy Models of Superposition | 10.48550/arxiv.2209.10652 | active | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Attractor and integrator networks in the brain | 10.1038/s41583-022-00642-0 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Neural Manifold Clustering and Embedding | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | On convex decision regions in deep network representations | 10.1038/s41467-025-60809-y | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Interpreting Neural Networks through the Polytope Lens | 10.48550/arxiv.2211.12312 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Geometric Sparse Coding in Wasserstein Space | 10.48550/arxiv.2210.12135 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Sparse autoencoders find highly interpretable features in language models | 10.48550/arxiv.2309.08600 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The linear representation hypothesis and the geometry of large language models | 10.48550/arxiv.2311.03658 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importa | 10.48550/arxiv.2306.07304 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to Ince | 10.48550/arxiv.2406.03662 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | On the Origins of Linear Representations in Large Language Models | 10.48550/arxiv.2403.03867 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Geometry of Categorical and Hierarchical Concepts in Large Language Models | 10.48550/arxiv.2406.01506 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Not all language model features are one-dimensionally linear | — | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Scaling and evaluating sparse autoencoders | 10.48550/arxiv.2406.04093 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Relational Composition in Neural Networks: A Survey and Call to Action | 10.48550/arxiv.2407.14662 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Measuring Progress in Dictionary Learning for Language Model Interpretability wi | 10.48550/arxiv.2408.00113 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencode | 10.48550/arxiv.2407.14435 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Recurrent neural networks learn to store and generate sequences using non-linear | 10.48550/arxiv.2408.10920 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A polar coordinate system represents syntax in large language models | 10.48550/arxiv.2412.05571 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Towards unifying interpretability and control: Evaluation via intervention | 10.48550/arxiv.2411.04430 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoenc | 10.48550/arxiv.2409.14507 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Batchtopk sparse autoencoders | 10.48550/arxiv.2412.06410 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Sparse Autoencoders Trained on the Same Data Learn Different Features | 10.48550/arxiv.2501.16615 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Open Problems in Mechanistic Interpretability | 10.48550/arxiv.2501.16496 | active | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Language models use trigonometry to do addition | 10.48550/arxiv.2502.00873 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders | 10.48550/arxiv.2501.17148 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Wo | 10.52202/085713-0140 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Are Sparse Autoencoders Useful? A Case Study in Sparse Probing | 10.48550/arxiv.2502.16681 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Geometry of Refusal in Large Language Models: Concept Cones and Representati | 10.48550/arxiv.2502.17420 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Archetypal sae: Adaptive and stable dictionary learning for concept extraction i | 10.48550/arxiv.2502.12892 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Learning Multi-Level Features with Matryoshka Sparse Autoencoders | 10.48550/arxiv.2503.17547 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geom | 10.48550/arxiv.2503.01822 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | From superposition to sparse codes: interpretable representations in neural netw | 10.48550/arxiv.2503.01824 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | On the emergence of linear analogies in word embeddings | 10.48550/arxiv.2505.18651 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The origins of representation manifolds in large language models | 10.48550/arxiv.2505.18235 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | From flat to hierarchical: Extracting sparse representations with matching pursu | 10.48550/arxiv.2506.03093 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Understanding sparse autoencoder scaling in the presence of feature manifolds | 10.48550/arxiv.2509.02565 | active | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders | 10.48550/arxiv.2507.23220 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Finding Manifolds With Bilinear Autoencoders | 10.48550/arxiv.2510.16820 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Into the rabbit hull: From task-relevant concepts in dino to minkowski geometry | 10.48550/arxiv.2510.08638 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | A circuit for predicting hierarchical structure in-context in Large Language Mod | 10.48550/arxiv.2509.21534 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | When Models Manipulate Manifolds: The Geometry of a Counting Task | 10.48550/arxiv.2601.04480 | active | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Priors in Time: Missing Inductive Biases for Language Model Interpretability | 10.48550/arxiv.2511.01836 | active | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for I | 10.48550/arxiv.2511.05541 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings | 10.48550/arxiv.2602.06218 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation | 10.48550/arxiv.2602.02315 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Context Structure Reshapes the Representational Geometry of Language Models | 10.48550/arxiv.2601.22364 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | Symmetry in language statistics shapes the geometry of model representations | 10.48550/arxiv.2602.15029 | referenced-only | s2-reference-walk |
| Do Sparse Autoencoders Capture Concept Manifolds? | The Information Geometry of Softmax: Probing and Steering | 10.48550/arxiv.2602.15293 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | System card: Claude Mythos preview | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | The Principles of Learning on Multiple Tasks | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Da | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Pareto frontiers in deep feature learning: Data, compute, width, and luck | 10.52202/075280-2082 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Effect of scale on catastrophic forgetting in neural networks | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Foundation Models from a Data-Distributional View | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | On a Theorem of Weyl Concerning Eigenvalues of Linear Transformations I. | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | DeepSeek-V3 Technical Report | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Natural Image Statistics - A Probabilistic Approach to Early Computational Visio | 10.1007/978-1-84882-491-1 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Multitask Learning | 10.1023/a:1007379606734 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Uncovering Latent Memories in Large Language Models | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Netw | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Deep Learning Scaling is Predictable, Empirically | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Zipf’s word frequency law in natural language: A critical review and future dire | 10.3758/s13423-014-0585-6 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask N | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Gradient based sample selection for online continual learning | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Multi-Task Learning as Multi-Objective Optimization | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Regularizing Deep Multi-Task Networks using Orthogonal Gradients | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Does learning require memorization? a short tale about a long tail | 10.1145/3357713.3384290 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | The Generalization Error of Random Features Regression: Precise Asymptotics and | 10.1002/cpa.22008 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Continual Learning in Neural Networks | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Orthogonal Gradient Descent for Continual Learning | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | A Constructive Prediction of the Generalization Error Across Scales | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Deep double descent: where bigger models and more data hurt | 10.1088/1742-5468/ac3a74 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Gradient Surgery for Multi-Task Learning | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | More Data Can Hurt for Linear Regression: Sample-wise Double Descent | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transforme | 10.48550/arxiv.1910.10683 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Optimal Regularization Can Mitigate Double Descent | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | A brief prehistory of double descent | 10.1073/pnas.2001875117 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Proving the Lottery Ticket Hypothesis: Pruning is All You Need | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Scaling Laws for Neural Language Models | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Suff | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Gradient Starvation: A Learning Proclivity in Neural Networks | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Scaling Laws for Autoregressive Generative Modeling | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Explaining neural scaling laws | 10.1073/pnas.2311878121 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Scaling Laws for Transfer | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | When is memorization of irrelevant training data necessary for high-accuracy lea | 10.1145/3406325.3451131 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Saddle-to-Saddle Dynamics in Deep Linear Networks: Small Initialization Training | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Conflict-Averse Gradient Descent for Multi-task Learning | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Scaling Language Models: Methods, Analysis & Insights from Training Gopher | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Quantifying Memorization Across Neural Language Models | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Training Compute-Optimal Large Language Models | 10.52202/068431-2176 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Li | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Scaling Laws and Interpretability of Learning from Repeated Data | 10.48550/arxiv.2205.10487 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | How catastrophic can catastrophic forgetting be in linear regression? | 10.48550/arxiv.2205.09588 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Emergent Abilities of Large Language Models | 10.48550/arxiv.2206.07682 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Memorization Without Overfitting: Analyzing the Training Dynamics of Large Langu | 10.48550/arxiv.2205.10770 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Measuring Forgetting of Memorized Training Examples | 10.48550/arxiv.2207.00099 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Revisiting Neural Scaling Laws in Language and Vision | 10.48550/arxiv.2209.06640 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | A Solvable Model of Neural Scaling Laws | 10.48550/arxiv.2210.16859 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | A picture of the space of typical learnable tasks | 10.48550/arxiv.2210.17011 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Large Language Models Struggle to Learn Long-Tail Knowledge | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Reduce, Reuse, Recycle: Improving Training Efficiency with Distillation | 10.48550/arxiv.2211.00683 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Progress measures for grokking via mechanistic interpretability | 10.48550/arxiv.2301.05217 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Data Selection for Language Models via Importance Resampling | 10.48550/arxiv.2302.03169 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics | 10.48550/arxiv.2302.11055 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Finding Alignments Between Interpretable Causal Variables and Distributed Neural | 10.48550/arxiv.2303.02536 | active | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining | 10.48550/arxiv.2305.10429 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | The Quantization Model of Neural Scaling | 10.48550/arxiv.2303.13506 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Larger language models do in-context learning differently | 10.48550/arxiv.2303.03846 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Grokking of Hierarchical Structure in Vanilla Transformers | 10.48550/arxiv.2305.18741 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Feature-Learning Networks Are Consistent Across Widths At Realistic Scales | 10.48550/arxiv.2305.18411 | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes | — | referenced-only | s2-reference-walk |
| Why Larger Models Learn More: Effects of Capacity, Interfere | Explaining grokking through circuit efficiency | 10.48550/arxiv.2309.02390 | referenced-only | s2-reference-walk |