Skip to main content

Training and Analyzing Sparse Autoencoders (SAEs)

Project description

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.

Join the Slack!

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

Citations and References

Research:

Reference Implementations:

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sae_lens-0.7.0.tar.gz (48.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

sae_lens-0.7.0-py3-none-any.whl (58.8 kB view details)

Uploaded Python 3

File details

Details for the file sae_lens-0.7.0.tar.gz.

File metadata

  • Download URL: sae_lens-0.7.0.tar.gz
  • Upload date:
  • Size: 48.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.3

File hashes

Hashes for sae_lens-0.7.0.tar.gz
Algorithm Hash digest
SHA256 02fc17620b14e073132119d826e041bbc4ac60de19f6c094f4a61e84d47736ee
MD5 d86cc6c57f919754468086adec386125
BLAKE2b-256 9bc9bd667c29a81c3ee6cd89a4e3f33f2c55779448c5bfa49b37cabf02459fda

See more details on using hashes here.

File details

Details for the file sae_lens-0.7.0-py3-none-any.whl.

File metadata

  • Download URL: sae_lens-0.7.0-py3-none-any.whl
  • Upload date:
  • Size: 58.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/5.0.0 CPython/3.12.3

File hashes

Hashes for sae_lens-0.7.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6425b2fa8eb2aa8eace42f28af6b6bf690b3c200e013b65af06ad081fc1e84ce
MD5 da14551f901730e398aa82c770ef6feb
BLAKE2b-256 e1963ad6ff218443ffb258907de2d9de6990b9d29ac0cbf113e617e6384187e4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page