concept
active
concept:attention-sink

Attention Sink

Phenomenon where layers concentrate most attention weight on the first token, captured by ColSum Concentration metric

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.

  • Per-head metric measuring fraction of attention weight concentrated on first token position
  • Attentionconcept0.788
    Selective attention mechanism is a component of GWT-2 indicator; AST-1 models and enables control over attention
  • Attention streamsconcept0.784
    Term introduced by this paper for the horizontal axis of information flow in transformers across token-positions via attention heads
  • Process using Q, K, V to compute a heat map over K and weighted sum of V.
  • Attention Decayconcept0.764
    Decrease in attention paid to system prompt over conversational turns, leading to persona fidelity degradation (cited from Li et al.)
  • Core operation in transformers, computing weighted combinations of previous elements
  • Attention headsconcept0.746
    Transformer attention heads that could be recruited to extract different kinds of information (text vs. thoughts).
  • The act of seeing and feeling the entire field of centers at a place, which Alexander equates with love of life.