lkopf/prism

[NeurIPS 2025] PRISM is a multi-concept feature description framework which can identify and score polysemantic features.

21
/ 100
Experimental

When analyzing how AI models make decisions, it can be hard to understand why certain features activate. This tool helps you go beyond single explanations for these features, providing multiple, human-understandable descriptions that capture the full complexity of what an AI feature represents. It takes model activations and outputs clear, clustered descriptions of the concepts the model is detecting. AI researchers and practitioners focused on model interpretability or explainable AI would use this.

No commits in the last 6 months.

Use this if you need to deeply understand the multiple concepts an AI model's internal features are responding to, moving beyond simplistic, single explanations.

Not ideal if you are looking for a simple, single-word explanation for every AI feature or if your primary goal is basic performance evaluation rather than interpretability.

AI-interpretability explainable-AI neural-network-analysis model-debugging concept-extraction
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 4 / 25
Maturity 7 / 25
Community 8 / 25

How are scores calculated?

Stars

8

Forks

1

Language

Jupyter Notebook

License

Last pushed

Aug 21, 2025

Commits (30d)

0

Get this data via API

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

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