paper
referenced-only
paper:deploying-interpretability-7b172c

Deploying 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