All tags
Catalogue tag

#mechanistic-interpretability

Every repository in the public record carrying this tag — from its GitHub topics or the keywords its package registries publish. Health is measured under the same versioned methodology as the rest of the record.

4 records
Tagged “mechanistic-interpretability”Ranked by health index
PyPI
92Excellenthealth index
decoderesearch/SAELens
Training Sparse Autoencoders on Language Models
Python · Jupyter Notebook★ 1,523↓ 40K/moSep 5, 2026
MITSep 5, 2026 · metrics 2.10.0
PyPI
51Moderatehealth index
mechbench/mechbench-compute
No repository description published.
Python★ 0↓ 7,795/moSep 15, 2026
No licenseSep 15, 2026 · metrics 2.10.0
PyPI
51Moderatehealth index
sae-probes/sae-probes
Sparse probing benchmark for Sparse Autoencoders derived from the paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"
Python★ 4↓ 2,477/moOct 16, 2026
MITOct 16, 2026 · metrics 2.10.0
PyPI
36Weakhealth index
mechbench/mechbench-runner
No repository description published.
Python★ 0↓ 3,609/moSep 30, 2026
No licenseSep 30, 2026 · metrics 2.10.0