A gentle introduction to sparse autoencoders

Our biggest leap so far in deciphering how large language models work

A gentle introduction to sparse autoencoders Our biggest leap so far in deciphering how large language models work Nick Jiang Jul 03, 2024 6 Share DALLE3: a lab technician wielding a sledgehammer to break open a black box Sparse autoencoders (SAEs) are the current hot topic 🔥 in the interpretability world. In late May, Anthropic released a paper that shows how to use sparse autoencoders to effectively break down the internal reasoning of Claude 3 (Anthropic’s LLM) 1 . Shortly after, OpenAI published a paper successfully applying a similar procedure for GPT4. What’s exciting about SAEs is that

related reading

• A gentle introduction to sparse autoencoders — LessWronglesswrong.com
• An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability | Adam Karvonenadamkarvonen.github.io
• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelsarxiv.org
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• An Intuitive Explanation of Sparse Autoencoders for Mechanistic Interpretability of LLMs — LessWronglesswrong.com
• Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
• Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
• pdfopenreview.net
• Llama Scope: Extracting Features from Llama 3.1-8B with SAEsarxiv.org
• [2409.14507] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencodersar5iv.labs.arxiv.org
• Do sparse autoencoders find "true features"? — LessWronglesswrong.com
• Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub