Sparse Autoencoder
https://github.com/openai/sparse_autoencoderAbout
OpenAI's reference implementation of sparse autoencoders for interpretability research on large language models.
Why it made the leaderboard
OpenAI's reference implementation of sparse autoencoders for LLM interpretability — start from the code the original researchers published instead of reimplementing the paper.
Tags
interpretabilitysparse-autoencoderresearchopenaillm
Tech Stack
Python
Comments (0)
No comments yet
Indexed by a proprietary survey. Corrections welcome.