paper:radford-2019-languageLanguage Models are Unsupervised Multitask Learners
Similar preprints — Semantic Scholar
Cited by (5)
- Understanding and Steering Llama 3 with Sparse Autoencoders - Goodfire
A sparse autoencoder trained on layer-19 residual-stream activations of Llama-3-8B-Instruct, using LMSYS-Chat-1M, yields features that can be labeled automatically, ranked by causal relevance, and use
- Measuring Faithfulness in Chain-of-Thought Reasoning
Chain-of-thought reasoning in a 175B RLHF-tuned assistant model is faithful only conditionally: how much the final answer depends on the stated reasoning swings from near zero to dominant by task, and
- Evaluating Language Model Character Traits
Claude-instant-1.2 achieves 91.1% accuracy and 88.6% logical coherence on 696 valid Leap-of-Thought entailment tuples — highest among 15 tested models including GPT-4 (89.9% accuracy, 84.7% coherence)
- The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?
Under arbitrarily powerful alignment maps, causal abstraction becomes vacuous: any neural network can be perfectly mapped to any algorithm, a result proven formally in Theorem 1 under five mild assump
- The Platonic Representation Hypothesis
Neural networks trained on different data modalities, architectures, and objectives are converging toward a shared statistical model of reality — what the paper terms the "platonic representation" — f