framework
active
framework:p-annealing-saeP-Annealing SAE
Evaluated architecture.
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Hybrid SAE jointly training turn-averaged inner and per-token outer partitions.
- Hybrid with separate turn-averaged and residual per-token SAEs.
- Interpretability method criticized in this paper for shattering manifolds into atomic pieces, obscuring overarching semantic structure.
- Interpretable features extracted by sparse autoencoders used as steering targets in this study
- The individual, supposedly monosemantic directions learned by SAEs; argued here to fragment manifolds into disconnected pieces.
- Interpretability tool underlying top-feature, details, steering tools.
- Adding a multiple of the SAE latent decoder vector to token activations to causally test each latent's role in misalignment
- Evaluated architecture.