Skip to content

joelburget/SAELens

 
 

Repository files navigation

Screenshot 2024-03-21 at 3 08 28 pm

SAE Lens

PyPI License: MIT build Deploy Docs codecov

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 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.

SAE Lens is the result of many contributors working collectively to improve humanities understanding of neural networks, many of whom are motivated by a desire to safeguard humanity from risks posed by artificial intelligence.

This library is maintained by Joseph Bloom and David Channin.

Tutorials

Join the Slack!

Feel free to join the Open Source Mechanistic Interpretability Slack for support!

Citations and References

Research:

Reference Implementations:

About

Training Sparse Autoencoders on Language Models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • HTML 98.0%
  • Python 1.4%
  • Other 0.6%