method
active
method:sparse-autoencoder-sae-features

Sparse autoencoder (SAE) features

Interpretability tool underlying top-feature, details, steering tools.

Neighborhood — ranked by edge-count

Methods (3)

method
  • Interpretability method criticized in this paper for shattering manifolds into atomic pieces, obscuring overarching semantic structure.
  • Sparse dictionary learning method used to extract interpretable features from EEG transformer embeddings.
  • Tool-using agent for open-ended model investigations.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.