interpretability: 13 curated resources
interpretability
13 resources · page 1 of 1
Transformer Circuits Thread
by Anthropic
Transformer Circuits Thread: Anthropic interpretability research series reverse-engineering transformer models.
Neuronpedia
by Neuronpedia
Neuronpedia: open-source interpretability platform for exploring sparse autoencoder features and circuits.
SAELens
SAELens GitHub repo: training and analysing sparse autoencoders on language models.
TransformerLens
TransformerLens GitHub repo: library for mechanistic interpretability of GPT-style language models.
Transluce
by Transluce
Transluce: nonprofit lab building open tools for AI oversight and interpretability.
Apollo Research: Science
Apollo Research science page listing its research and pre-deployment evaluations on AI scheming and mitigations.
Interpretable Machine Learning
Christoph Molnar's Interpretable Machine Learning book: free online guide to explainability methods and their limits.
How To Become A Mechanistic Interpretability Researcher
by Neel Nanda
Neel Nanda's AI Alignment Forum guide on how to become a mechanistic interpretability researcher, which replaced his earlier getting-started page.
Goodfire research
by Goodfire
Goodfire research page: interpretability research on understanding and editing the internals of AI models.
InterpretML
InterpretML: open-source toolkit for glassbox models and explaining ML model behaviour.
Tracing the thoughts of a large language model
by Anthropic
Anthropic interpretability research tracing internal mechanisms of Claude with attribution graphs.
A Mathematical Framework for Transformer Circuits
by Anthropic
Anthropic Transformer Circuits paper A Mathematical Framework for Transformer Circuits (2021).
On the Biology of a Large Language Model
by Anthropic
Anthropic Transformer Circuits paper On the Biology of a Large Language Model: attribution graphs on Claude 3.5 Haiku.