WolodjaZ/MSAE

Interpreting CLIP with Hierarchical Sparse Autoencoders (ICML 2025)

47
/ 100
Emerging

This project helps AI researchers and practitioners better understand how large vision-language models like CLIP interpret images and text. It takes pre-computed activations from these models and generates hierarchical, interpretable features that reveal the semantic concepts the model uses. This allows researchers to analyze model biases and perform concept-based similarity searches, ultimately leading to more controllable and explainable AI systems.

Use this if you need to extract and analyze understandable concepts from complex vision-language models to improve their interpretability and control.

Not ideal if you are primarily interested in general-purpose model training or fine-tuning without a specific focus on interpretability.

AI-interpretability vision-language-models model-analysis AI-explainability concept-extraction
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

22

Forks

6

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 17, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/WolodjaZ/MSAE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.