interp-lab
An open LLM interpretability tool that helps researchers and AI agents identify LLM activations and features and make Sparse Auto Encoders as needed.
- Latest release
- 6h ago
- Releases
- 8
- Known CVEs
- 0
- First release
- May 18, 2026
- License
- MIT
Repository
Source
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Language
- Python
- interpretability
- llm
- pytorch
- sae
- sparse-autoencoder
- sparse-autoencoders
Security score
No OpenSSF Scorecard available for this repository.
Packages from this repo
No other tracked packages from this repository.
Insights
Activity
- Total releases
- 8
- Last 12 months
- 8
- Cadence
- ~daily
- Dependencies
- 16
Releases per month
last 12 monthsRelease mix
- major 3
- minor 4
8
releases
Dependencies
Depends on
3.1.0-
build
>=1.2
-
goodfire
>=0.3
-
huggingface-hub
>=1.0
-
hypothesis
>=6.155
-
llama-cpp-python
>=0.3
-
modal
>=1.4
-
nnsight
>=0.6
-
pytest
>=8.0
-
pyyaml
>=6.0
-
sae-lens
>=6.0
1–10 of 16
Used by
Nothing tracked depends on this yet.
Releases
| Version | Released | |
|---|---|---|
3.1.0
minor
| ||
3.0.0
major
| ||
2.3.0
minor
| ||
2.2.0
minor
| ||
2.0.0
major
| ||
1.0.0
major
| ||
0.2.0
minor
| ||
0.1.0
initial
|