Blog Post··11 min read
Representation Geometry: How Neural Networks Encode Meaning
The linear representation hypothesis, superposition, polysemanticity, and why transformer activations are more structured than they look.
Tag: superposition
Blog Post··11 min read
Sparse Autoencoders: Decomposing Neural Networks into Interpretable Features
Dictionary learning for neural networks — how sparse autoencoders recover monosemantic features from polysemantic activations, and what Anthropic's scaling monosemanticity work found in Claude.