paper
referenced-only
paper:deploying-interpretability-7b172cDeploying interpretability to production with rakuten: Sae probes for pii detection
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