https://jbloomaus.github.io/SAELens/
Training Sparse Autoencoders on Language Models
https://jbloomaus.github.io/SAELens/
Last synced: 2 months 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 (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-08-18T10:40:24.000Z (about 1 year ago)
- Last Synced: 2024-08-18T11:13:17.049Z (about 1 year 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-python - jbloomaus.github.io/saelens
README
# SAE Lens
[](https://pypi.org/project/sae-lens/)
[](https://opensource.org/licenses/MIT)
[](https://github.com/jbloomAus/SAELens/actions/workflows/build.yml)
[](https://github.com/jbloomAus/SAELens/actions/workflows/deploy_docs.yml)
[](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/), [Curt Tigges](https://curttigges.com/), [Anthony Duong](https://github.com/anthonyduong9) 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.
## Migrating to SAELens v6
The new v6 update is a major refactor to SAELens and changes the way training code is structured. Check out the [migration guide](https://jbloomaus.github.io/SAELens/latest/migrating/) for more details.
## Tutorials
- [SAE Lens + Neuronpedia](tutorials/tutorial_2_0.ipynb)[](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)
[](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)
[](https://githubtocolab.com/jbloomAus/SAELens/blob/main/tutorials/logits_lens_with_features.ipynb)
- [Training a Sparse Autoencoder](tutorials/training_a_sparse_autoencoder.ipynb)
[](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-375zalm04-GFd5tdBU1yLKlu_T_JSqZQ) for support!
## Citation
Please cite the package as follows:
```
@misc{bloom2024saetrainingcodebase,
title = {SAELens},
author = {Bloom, Joseph and Tigges, Curt and Duong, Anthony and Chanin, David},
year = {2024},
howpublished = {\url{https://github.com/jbloomAus/SAELens}},
}
```