Attention

Selective attention mechanism is a component of GWT-2 indicator; AST-1 models and enables control over attention

Neighborhood — ranked by edge-count

paper

concept

Self-attention
related_to
A form of key-query attention within a single input sequence; core to Transformers.
Attention heads
related_to
Transformer attention heads that could be recruited to extract different kinds of information (text vs. thoughts).
attention computation
related_to
Process using Q, K, V to compute a heat map over K and weighted sum of V.

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.

Attention streamsconcept0.842
Term introduced by this paper for the horizontal axis of information flow in transformers across token-positions via attention heads
attention mechanismconcept0.841
Core operation in transformers, computing weighted combinations of previous elements
Attention Schemaconcept0.836
A predictive model representing and controlling attention; central to attention schema theory.
Attention Decayconcept0.822
Decrease in attention paid to system prompt over conversational turns, leading to persona fidelity degradation (cited from Li et al.)
Focused Attention Cycleconcept0.814
Formal model of meditation phenomenology: focus → distraction → awareness of distraction → redirection, derived from active inference.
paying attention to the wholenessconcept0.810
The act of seeing and feeling the entire field of centers at a place, which Alexander equates with love of life.
Attentional Stateconcept0.808
Higher-order generative model variables modulating perceptual precision; subject to policy selection (deliberate shifts of attention).
attentional modeconcept0.807
Variable aperture of attention, ranging from collapsed to expanded; human and model analogs.