chrisliu298/awesome-sparse-autoencoders

A resource repository of sparse autoencoders for large language models

20
/ 100
Experimental

This repository helps AI researchers and machine learning engineers stay current with the latest advancements in sparse autoencoders, particularly for understanding how large language models (LLMs) work internally. It curates a comprehensive list of academic papers and blog posts on this topic. You get a structured overview of research, which is valuable for anyone focused on mechanistic interpretability of LLMs.

No commits in the last 6 months.

Use this if you are an AI researcher or machine learning engineer actively involved in understanding or developing mechanistic interpretability for large language models.

Not ideal if you are looking for ready-to-use code, a tutorial for building sparse autoencoders, or general information on LLMs without a focus on their internal mechanisms.

AI-research LLM-interpretability mechanistic-interpretability machine-learning-engineering AI-safety
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

License

Apache-2.0

Last pushed

Sep 11, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/chrisliu298/awesome-sparse-autoencoders"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.