Factual package intelligence from PyPI

sae-probes 0.4.0 package intelligence

Sparse probing benchmark for Sparse Autoencoders derived from the paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"

pip install sae-probes

Current version
0.4.0
Python requirement
<4.0,>=3.10
License
MIT
Distribution type
Pure Python wheel
Release files
2 (1 wheels, 1 source)
Download size
85.9 MiB
Release history
9 releases with files
Median release cadence
4 days

sae-probes dependencies

PyPI declares 7 unique dependency rules for this release. Environment markers are shown when supplied by the project.

  1. hf-transfer <0.2.0,>=0.1.9
  2. pandas <3.0.0,>=2.2.3
  3. sae-lens <7.0.0,>=5.0.0
  4. scikit-learn <2.0.0,>=1.6.1
  5. transformer-lens <3.0.0,>=2.15.4
  6. xgboost <4.0.0,>=3.0.2
  7. zstandard >=0.19.0

Compatibility and release files

sae-probes publishes 1 wheel and 1 source archive for version 0.4.0. Wheel platform tags: any.

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

Release activity and sources

PyPI lists 9 releases with files. The first dated release is ; 9 releases fall within the 365 days preceding the latest dated release. The current release files were uploaded on . The preceding dated release was .