paper
referenced-only
1974
paper:doi-10-1111-j-2517-6161-1974-tb00999-xSpatial Interaction and the Statistical Analysis of Lattice Systems
ByJ. Besag
Similar preprints — Semantic Scholar
Cited by (1)
- 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