Activation Atlases

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Jan 13 11:50
Editor
Edited
Edited
2025 Jun 30 14:7
Refs
The word "Atlas" refers to a "map" or "collection" that systematically organizes various parts, visually structuring the internal representations of models (e.g., attention, activation, etc.).
Activation Atlases cut the activation maps of each network layer into patches, cluster these patches, and arrange them on a 2D map using t-SNE/UMAP.
 
 

SemanticLens

Unlike Activation Atlas which directly uses activation patches, this method analyzes neuron-level patches by cutting top-m neurons using CRP (Concept Relevance Propagation) and embedding them into CLIP's semantic space. Also it provided interpretability metric such as Clarity, Redundancy, Polysemanticity.
Great demonstration with
CLIP
Vision Transformer
using UMAP visualization
 
 

Recommendations