A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
arxiv.org · 6,328 words · saved by 2 readers
N/A
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models Dong Shu1,† , Xuansheng Wu2,† , Haiyan Zhao3,† , Daking Rai4 , Ziyu Yao4 , Ninghao Liu2 , Mengnan Du3 1 Northwestern University 2 University of Georgia…
saved by
related reading
- 2408.14690arxiv.org
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- Esoteric Language Modelsarxiv.org
- Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
- An Intuitive Explanation of Sparse Autoencoders for LLM Interpretability | Adam Karvonenadamkarvonen.github.io
- A gentle introduction to sparse autoencoders — LessWronglesswrong.com
- Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Modelsarxiv.org
- Towards Monosemanticity: Decomposing Language Models With Dictionary Learningtransformer-circuits.pub
- [2309.08600] Sparse Autoencoders Find Highly Interpretable Features in Language Modelsarxiv.org
- SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretabilityarxiv.org
- Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
- A gentle introduction to sparse autoencodersnickjiang.substack.com