paper:gurnee-finding-neurons-in-a-haystack-case-studi-2023Finding neurons in a haystack: Case studies with sparse probing
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- ≈ 74%
- Neural mechanisms of predictive processing: a collaborative community experiment through the OpenScope programNicholas Audette, Ryszard Auksztulewicz, Krzysztof Basi\'nski, Andr\'e M. Bastos, Michael Berry, Andres Canales-Johnson, Hannah Choi, Claudia Clopath, Uri Cohen, Rui Ponte Costa, Roberto De Filippo, Roman Doronin, S\'everine Durand, Steven P. Errington, Jeffrey P. Gavornik, Colleen J. Gillon, Arno Granier, Jordan P. Hamm, Loreen Hert\"ag, Henry Kennedy, Sandeep Kumar, Alexander Ladd, Hugo Ladret, J\'er\^ome A. Lecoq, Alexander Maier, Patrick McCarthy, Jie Mei, Jorge Mejias, John Hongyu Meng, Fabian Mikulasch, Noga Mudrik, Farzaneh Najafi, Kevin Nejad, Hamed Nejat, Karim Oweiss, Mihai A. Petrovici, Viola Priesemann, Lucas Rudelt, Sarah Ruediger, Simone Russo, Alessandro Salatiello, Walter Senn, Eli Sennesh, Sepehr Sima, Cem Uran, Anna Vasilevskaya, Julien Vezoli, Martin Vinck, Xiao-Jing Wang, Jacob A. Westerberg, Katharina Wilmes, Yihan Sophy Xiong Ido Aizenbud2026≈ 73%
- Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch InterventionsDhruv Kumar Manan Gupta2025≈ 73%
- Selective Neuron Amplification in Transformer Language ModelsPayal Pahwa, Monika Arora Ryyan Akhtar2026≈ 73%
- Much Easier Said Than Done: Falsifying the Causal Relevance of Linear Decoding MethodsAbhijit Suresh, Hunar Jain, Rahul Kumar, R. McKell Carter Lucas Hayne2022≈ 73%
- Disentangling Neuron Representations with Concept VectorsVincent Andrearczyk, Henning Muller, Mara Graziani Laura O'Mahony2023≈ 72%
- Simulations Approaching Data: Cortical Slow Waves in Inferred Models of the Whole Hemisphere of MouseChiara De Luca, Giulia De Bonis, Robin Gutzen, Irene Bernava, Elena Pastorelli, Francesco Simula, Cosimo Lupo, Leonardo Tonielli, Anna Letizia Allegra Mascaro, Francesco Resta, Francesco Pavone, Micheal Denker, Pier Stanislao Paolucci Cristiano Capone2026≈ 72%
- How much neuroscience does a neuroscientist need to know?James C.R. Whittington and William Dorrell2026≈ 72%
- Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label InformationSehyun Lee, Jaesik Choi Youngju Joung2025≈ 72%
- Understanding and Detecting Hallucinations in Neural Machine Translation via Model IntrospectionSweta Agrawal, Eleftheria Briakou, Marianna J. Martindale, Marine Carpuat Weijia Xu2023≈ 72%
- PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant CircuitsErblina Purelku, Johanna Vielhaben, Wojciech Samek, Sebastian Lapuschkin Maximilian Dreyer2024≈ 72%
- Finding Similar Objects and Active Inference for Surprise in Numenta Neocortex ModelHajime Kawakami2025≈ 72%
- Being curious about the answers to questions: novelty search with learned attentionMartin Biehl, Nathaniel Virgo, Ryota Kanai Nicholas Guttenberg2018≈ 72%
- ≈ 72%
- ≈ 72%
- Toy Models of Superpositionin corpus2022≈ 71%
- ≈ 71%
- Learning without neurons in physical systemsin corpus2022≈ 70%
- Zoom In: An Introduction to Circuitsin corpus2020≈ 70%
- Collective intelligence: A unifying concept for integrating biology across scales and substratesin corpus2024≈ 69%
- Model Alignment Searchin corpus2025≈ 69%
- The computational boundary of a 'self': developmental bioelectricity drives multicellularity and scale-free cognitionin corpus2019≈ 69%
- ≈ 69%
- ≈ 69%
- Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representationsin corpus2023≈ 69%
- ≈ 69%
- Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retentionin corpus2026≈ 69%
- ≈ 68%
Similar preprints — Semantic Scholar
Cited by (5)
- When Models Manipulate Manifolds: The Geometry of a Counting Task
Claude 3.5 Haiku's linebreaking in fixed-width text is implemented by manipulating low-dimensional, rippled 1-D feature manifolds: character count, line width, characters remaining and next-token leng
- SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
Gains on the sparsity-fidelity frontier do not predict how well a sparse autoencoder performs on downstream tasks, and SAEBench demonstrates this by scoring over 200 SAEs on eight metrics. Matryoshka
- Persona Features Control Emergent Misalignment
Fine-tuning GPT-4o on narrowly incorrect datasets—spanning nine domains including health, legal, and automotive advice—generalizes into broadly malicious behavior across unrelated prompts, confirming
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
At sufficient scale, LLMs linearly represent the truth or falsehood of factual statements in their internal activations — a claim supported by PCA visualizations, cross-dataset probe transfer, and cau
- Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts
Llama-3.1-8B solves cyclic arithmetic (e.g., "what month is six months after August?") not by performing modular addition in the period of the cyclic concept (12 for months, 7 for days of the week) as