https://jbloomaus.github.io/SAELens/

Training Sparse Autoencoders on Language Models
https://jbloomaus.github.io/SAELens/

Last synced: 4 days ago
JSON representation

Training Sparse Autoencoders on Language Models

• Host: GitHub
• URL: https://jbloomaus.github.io/SAELens/
• Owner: jbloomAus
• License: mit
• Created: 2023-11-29T10:37:55.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-08-18T10:40:24.000Z (5 months ago)
• Last Synced: 2024-08-18T11:13:17.049Z (5 months ago)
• Language: HTML
• Homepage: https://jbloomaus.github.io/SAELens/
• Size: 165 MB
• Stars: 313
• Watchers: 8
• Forks: 86
• Open Issues: 21
• Metadata Files:
  • Readme: README.md
  • Changelog: CHANGELOG.md
  • Contributing: docs/contributing.md
  • License: LICENSE
  • Roadmap: docs/roadmap.md

Awesome Lists containing this project

• Awesome-Local-LLM - Link
• Awesome-Local-LLM - Link

README

        


# SAE Lens 

[![PyPI](https://img.shields.io/pypi/v/sae-lens?color=blue)](https://pypi.org/project/sae-lens/)

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)

[![build](https://github.com/jbloomAus/SAELens/actions/workflows/build.yml/badge.svg)](https://github.com/jbloomAus/SAELens/actions/workflows/build.yml)

[![Deploy Docs](https://github.com/jbloomAus/SAELens/actions/workflows/deploy_docs.yml/badge.svg)](https://github.com/jbloomAus/SAELens/actions/workflows/deploy_docs.yml)

[![codecov](https://codecov.io/gh/jbloomAus/SAELens/graph/badge.svg?token=N83NGH8CGE)](https://codecov.io/gh/jbloomAus/SAELens)

SAELens exists to help researchers:

- Train sparse autoencoders.

- Analyse sparse autoencoders / research mechanistic interpretability. 

- Generate insights which make it easier to create safe and aligned AI systems.

Please refer to the [documentation](https://jbloomaus.github.io/SAELens/) for information on how to:

- Download and Analyse pre-trained sparse autoencoders. 

- Train your own sparse autoencoders.

- Generate feature dashboards with the [SAE-Vis Library](https://github.com/callummcdougall/sae_vis/tree/main).

SAE Lens is the result of many contributors working collectively to improve humanity's understanding of neural networks, many of whom are motivated by a desire to [safeguard humanity from risks posed by artificial intelligence](https://80000hours.org/problem-profiles/artificial-intelligence/).

This library is maintained by [Joseph Bloom](https://www.jbloomaus.com/) and [David Chanin](https://github.com/chanind).

## Loading Pre-trained SAEs. 

Pre-trained SAEs for various models can be imported via SAE Lens. See this [page](https://jbloomaus.github.io/SAELens/sae_table/) in the readme for a list of all SAEs.

## Tutorials

- [SAE Lens + Neuronpedia](tutorials/tutorial_2_0.ipynb)[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/tutorial_2_0.ipynb)

- [Loading and Analysing Pre-Trained Sparse Autoencoders](tutorials/basic_loading_and_analysing.ipynb)

 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/basic_loading_and_analysing.ipynb)

 - [Understanding SAE Features with the Logit Lens](tutorials/logits_lens_with_features.ipynb)

 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/logits_lens_with_features.ipynb)

  - [Training a Sparse Autoencoder](tutorials/training_a_sparse_autoencoder.ipynb)

 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/training_a_sparse_autoencoder.ipynb)

## Join the Slack!

Feel free to join the [Open Source Mechanistic Interpretability Slack](https://join.slack.com/t/opensourcemechanistic/shared_invite/zt-2k0id7mv8-CsIgPLmmHd03RPJmLUcapw) for support!

## Citation

Please cite the package as follows:

```

@misc{bloom2024saetrainingcodebase,

   title = {SAELens},

   author = {Joseph Bloom, Curt Tigges and David Chanin},

   year = {2024},

   howpublished = {\url{https://github.com/jbloomAus/SAELens}},

}

```