Skip to main content
saes_pic

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.

SAELens inference works with any PyTorch-based model, not just TransformerLens. While we provide deep integration with TransformerLens via SAETransformerBridge and HookedSAETransformer, SAEs can be used with Hugging Face Transformers, NNsight, or any other framework by extracting activations and passing them to the SAE's encode() and decode() methods.

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 humanity's 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, Curt Tigges, Anthony Duong and David Chanin.

Loading Pre-trained SAEs.

Pre-trained SAEs for various models can be imported via SAE Lens. See this page 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 for more details.

Tutorials

Join the Slack!

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

Other SAE Projects

  • dictionary-learning: An SAE training library that focuses on having hackable code.
  • Sparsify: A lean SAE training library focused on TopK SAEs.
  • Overcomplete: SAE training library focused on vision models.
  • SAE-Vis: A library for visualizing SAE features, works with SAELens.
  • SAEBench: A suite of LLM SAE benchmarks, works with SAELens.

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/decoderesearch/SAELens}},
}

Metadata

Release files for sae-lens 6.55.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sae-lens 6.55.2
File Size Uploaded Provenance Actions
sae_lens-6.55.2.tar.gz 293.9 kB With provenance Details for sae_lens-6.55.2.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for sae-lens 6.55.2
File Interpreter ABI Platform Actions
sae_lens-6.55.2-py3-none-any.whl Python 3 none any Details for sae_lens-6.55.2-py3-none-any.whl

Total release size: 618.9 kB

Release files / sae_lens-6.55.2.tar.gz

Download URL sae_lens-6.55.2.tar.gz
Size 293.9 kB
Tags Source
SHA-256 checksum
How to use checksums
38cc2b288d1df3fe38f372bdc5ab90e45930665534b0af1561e872aeab4ab16b
BLAKE2b-256 checksum
How to use checksums
d33fa8f543f38e9dfc2437e72122a105f39a78d2e9d13bf2949f71a9f5b8cde6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 11, 2026.

Transparency log

Release files / sae_lens-6.55.2-py3-none-any.whl

Download URL sae_lens-6.55.2-py3-none-any.whl
Size 325.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
a1b4a41adaef5a24d98439e969a275ca4c9b71a01b67fce922955a569e01fc36
BLAKE2b-256 checksum
How to use checksums
d1bcafb4faa117bd7927290d2376162666292bf179dc92986c7977b51cf5dd79
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 11, 2026.

Transparency log

Security for sae-lens 6.55.2

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for sae_lens-6.55.2.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 11, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

6.55.2 This release

2 release files Full provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page