KempnerInstitute/overcomplete
👋 Overcomplete is a Vision-based SAE Toolbox
This library helps machine learning researchers and practitioners understand what visual concepts large AI models are learning. It takes the internal activations from a vision model and extracts meaningful, interpretable concepts, letting you see what features the model detects. Researchers and engineers working with vision models would use this to explain and debug their models.
127 stars.
Use this if you are developing or studying large vision models and need to extract and visualize the underlying visual concepts the model has learned.
Not ideal if you are looking for a general-purpose machine learning library or a tool for natural language processing models, as it's specifically for vision-based sparse autoencoders.
Stars
127
Forks
5
Language
Python
License
MIT
Category
Last pushed
Dec 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KempnerInstitute/overcomplete"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
opencv/opencv
Open Source Computer Vision Library
pytorch/vision
Datasets, Transforms and Models specific to Computer Vision
kornia/kornia
🐍 Geometric Computer Vision Library for Spatial AI
ermig1979/Simd
C++ image processing and machine learning library with using of SIMD: SSE, AVX, AVX-512, AMX ...
open-edge-platform/training_extensions
Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™