4 stories tagged mechanistic-interpretability, newest first.
768 points by themgt | 300 comments
An informal research essay by Nick Cammarata at Goodfire arguing polysemanticity stems from fixable issues, not superposition, making neurons interpretable at scale.
987 points by Philpax | 356 comments
Anthropic research post from March 2025 describing interpretability work that traces the internal computations of its Claude language model.
542 points by PaulPauls | 80 comments
GitHub repository with an end-to-end PyTorch pipeline for LLM interpretability using sparse autoencoders on Llama 3.2, replicating Anthropic/OpenAI/DeepMind research.
402 points by tompark | 58 comments
Anthropic research post from Oct 2023 on decomposing language model neurons into more interpretable features.