Clip Dissect

Use this skill when you need to automatically describe or interpret the functionality of individual neurons in deep neural networks (DNNs) using CLIP-based semantic analysis, perform mechanistic interpretability research on vision models, dissect convolutional or transformer-based image classifiers, identify what visual concepts activate specific neurons, or compare neuron descriptions across different probing datasets and concept sets.

zjunlp Updated 1.5k repo stars

File contents

zjunlp/mechanist commit 9f42e7ea7a

Frequently asked questions

npx get-skill add zjunlp/clip-dissect