jim-berend/semanticlens
Mechanistic understanding and validation of large AI models with SemanticLens
This tool helps AI researchers and practitioners understand why large vision models make certain predictions. You provide your trained image model and a dataset, and it shows you what specific internal components (like neurons or filters) are 'seeing' or reacting to, translated into human-understandable concepts. This allows you to explain, debug, and validate the model's inner workings.
Use this if you need to gain a mechanistic understanding of what your large vision model has learned and how it processes visual information.
Not ideal if you are looking for a tool to train or fine-tune AI models, or if you primarily work with non-vision data types.
Stars
51
Forks
2
Language
Python
License
BSD-3-Clause
Last pushed
Dec 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jim-berend/semanticlens"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
obss/sahi
Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
tensorflow/tcav
Code for the TCAV ML interpretability project
MAIF/shapash
🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent...
TeamHG-Memex/eli5
A library for debugging/inspecting machine learning classifiers and explaining their predictions
csinva/imodels
Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling...