method
active
method:attention-sink-scoreAttention Sink Score
Per-head metric measuring fraction of attention weight concentrated on first token position
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.
- Phenomenon where layers concentrate most attention weight on the first token, captured by ColSum Concentration metric
- Term introduced by this paper for the horizontal axis of information flow in transformers across token-positions via attention heads
- Fraction of attention heads with sink score above threshold 0.3, used to track stages of inference
- Process using Q, K, V to compute a heat map over K and weighted sum of V.
- Weighted Spearman correlation that corrects for sampling bias in automated interpretability evaluation
- Dot product between hidden state and concept vector averaged across 5-layer window around best layer; measures model's internal emotive state
- Decrease in attention paid to system prompt over conversational turns, leading to persona fidelity degradation (cited from Li et al.)
- Selective attention mechanism is a component of GWT-2 indicator; AST-1 models and enables control over attention