concept
active
concept:attention-streams

Attention streams

Term introduced by this paper for the horizontal axis of information flow in transformers across token-positions via attention heads

Neighborhood — ranked by edge-count

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.

  • Attentionconcept0.842
    Selective attention mechanism is a component of GWT-2 indicator; AST-1 models and enables control over attention
  • Process using Q, K, V to compute a heat map over K and weighted sum of V.
  • Streamconcept0.806
    An infinite sequence data type with semantics as functions from Nat to a.
  • Formal model of meditation phenomenology: focus → distraction → awareness of distraction → redirection, derived from active inference.
  • Attention Sinkconcept0.784
    Phenomenon where layers concentrate most attention weight on the first token, captured by ColSum Concentration metric
  • Attention headsconcept0.783
    Transformer attention heads that could be recruited to extract different kinds of information (text vs. thoughts).
  • data streamsconcept0.782
    Partially instantiated lists used to implement communication channels in logic languages.
  • Core operation in transformers, computing weighted combinations of previous elements