Factual package intelligence from PyPI

sae-bench 0.6.0 package intelligence

A framework for evaluating sparse autoencoders

pip install sae-bench

Current version
0.6.0
Python requirement
<4.0,>=3.10
License
Not declared
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
532.7 KiB
Release history
11 releases with files
Median release cadence
43 days

sae-bench dependencies

PyPI declares 20 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. beartype >=0.14.1
  2. collectibles >=0.1.5
  3. datasets <4.0.0,>=3.0.0
  4. einops >=0.8.0
  5. jaxtyping >=0.2.25
  6. matplotlib >=3.8.4
  7. numpy <2.0,>=1.26.4
  8. openai >=1.0.0
  9. pandas >=2.1.2
  10. plotly >=5.22.0
  11. pydantic >=2.9.2
  12. sae-probes <0.5.0,>=0.4.0
  13. sae_lens <7.0.0,>=6.28.0
  14. scikit-learn >=1.5.2
  15. seaborn >=0.13.2
  16. tabulate >=0.9.0
  17. torch >=2.1.0
  18. torchvision >=0.16.1

The compact report shows 18 of 20 declarations. The interactive dependency graph loads the complete metadata.

Compatibility and release files

sae-bench publishes 1 wheel and 1 source archive for version 0.6.0. Wheel platform tags: any.

Declared Python classifiers: 3.10, 3.11, 3.12, 3.13, 3.14.

Security snapshot for sae-bench 0.6.0

An OSV query completed on and found 0 known vulnerabilities affecting this version. 0 advisories are classified as critical. 0 advisories appear in the CISA Known Exploited Vulnerabilities catalog.

Metadata completeness

PyPI does not currently declare: license. PyDeps marks these fields as unknown instead of guessing values.

Release activity and sources

PyPI lists 11 releases with files. The first dated release is ; 4 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .