framework
active
framework:attention-output-saes

Attention-output SAEs

Decomposition approach with rank-1 OV directions.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

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.

  • Second checkpointing strategy.
  • Attentionconcept0.787
    Selective attention mechanism is a component of GWT-2 indicator; AST-1 models and enables control over attention
  • The specific activation representation used: output of ℓ-th attention block = MLP output + residual stream.
  • Internal concepts a model uses, extracted as human-interpretable components.
  • Attention streamsconcept0.761
    Term introduced by this paper for the horizontal axis of information flow in transformers across token-positions via attention heads
  • Attention Schemaconcept0.760
    A predictive model representing and controlling attention; central to attention schema theory.
  • Attentional features spread across multiple heads.
  • SAE featuresconcept0.756
    The individual, supposedly monosemantic directions learned by SAEs; argued here to fragment manifolds into disconnected pieces.