mechanistic interpretability

Successor Heads: Recurring, Interpretable Attention Heads In The Wild ICLR 2024 Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models NeurIPS 2024 The Mystery of In-Context Learning: A Comprehensive Survey on Interpretation and Analysis EMNLP 2024 Towards Best Practices of Activation Patching in Language Models: Metrics and Methods ICLR 2024 Towards Interpretable Sequence Continuation: Analyzing Shared Circuits in Large Language Models EMNLP 2024 Transcoders find interpretable LLM feature circuits NeurIPS 2024 Transformers Represent Belief State Geometry in their Residual Stream NeurIPS 2024 Understanding Addition in Transformers ICLR 2024 Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models EMNLP 2024 What Makes and Breaks Safety Fine-tuning? A Mechanistic Study NeurIPS 2024 Where does In-context Learning Happen in Large Language Models? NeurIPS 2024 Analyzing Vision Transformers for Image Classification in Class Embedding Space NeurIPS 2023 A Toy Model of Universality: Reverse Engineering how Networks Learn Group Operations ICML 2023 How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model NeurIPS 2023 Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small ICLR 2023 Learning Transformer Programs NeurIPS 2023 Progress measures for grokking via mechanistic interpretability ICLR 2023 Scale Alone Does not Improve Mechanistic Interpretability in Vision Models NeurIPS 2023 The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks NeurIPS 2023 Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models EMNLP 2023 Towards Automated Circuit Discovery for Mechanistic Interpretability NeurIPS 2023 Tracr: Compiled Transformers as a Laboratory for Interpretability NeurIPS 2023 Tracing and Manipulating intermediate values in Neural Math Problem Solvers EMNLP 2022