The Geometry of Concepts: Sparse Autoencoder Feature Structure
arxiv.org · 5,861 words · saved by 1 readers
N/A
Article The Geometry of Concepts: Sparse Autoencoder Feature Structure Yuxiao Li 4,†, , Eric J. Michaud 1,3,† , David D. Baek 2,3,† , Joshua Engels 2 , Xiaoqing Sun 1 and Max Tegmark 1,3 * 1 Department of Physics, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA; ericjm@mit.edu (E.J.M.);…
related reading
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability | Adam Karvonenadamkarvonen.github.io
- A gentle introduction to sparse autoencoders — LessWronglesswrong.com
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub
- Matryoshka Sparse Autoencoders — LessWronglesswrong.com
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- pdfopenreview.net
- Do sparse autoencoders find "true features"? — LessWronglesswrong.com
- Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
- A gentle introduction to sparse autoencodersnickjiang.substack.com
- Toy Models of Superpositiontransformer-circuits.pub
- Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnettransformer-circuits.pub