paper
referenced-only
2003
paper:doi-10-1073-pnas-1031596100Hessian eigenmaps: Locally linear embedding techniques for high-dimensional data
ByD. Donoho·C. Grimes
Similar preprints — Semantic Scholar
Cited by (2)
- Do Sparse Autoencoders Capture Concept Manifolds?
Sparse autoencoders trained on Llama3.1-8B (layer 19, 500M Pile tokens, 25 SAEs across Standard, JumpReLU, TopK, BatchTopK and Matryoshka architectures at VE > 0.85) do not capture continuous concept
- Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
Lifting the featurizer's atom from a direction to a block of directions recovers concept manifolds that SAEs shatter, and block sparsity is the MAP-matched prior for a representation that is a sparse