#sparse-autoencoders News & Analysis

77 articles tagged with #sparse-autoencoders. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.

77 articles

AINeutralarXiv – CS AI · May 95/10

🧠

From Token Lists to Graph Motifs: Weisfeiler-Lehman Analysis of Sparse Autoencoder Features

Researchers introduce a novel graph-based analysis method for sparse autoencoders (SAEs) in transformer models, using Weisfeiler-Lehman graph kernels to examine token co-occurrence patterns in SAE features. Applied to GPT-2 Small, this approach identifies structural motif families that traditional decoder weight analysis misses, revealing complementary insights into how neural networks organize semantic information.

AINeutralarXiv – CS AI · Mar 24/107

🧠

Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry

Researchers analyzed DINOv2 vision transformer using Sparse Autoencoders to understand how it processes visual information, discovering that the model uses specialized concept dictionaries for different tasks like classification and segmentation. They propose the Minkowski Representation Hypothesis as a new framework for understanding how vision transformers combine conceptual archetypes to form representations.

← PrevPage 4 of 4