concept
active
concept:autoregressive-recurrence

autoregressive recurrence

Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker
  • janus
    studies
    Author of foundational X thread on transformer information flow; central theoretical contribution to understanding introspection architecture.

Claims (1)

claim

Methods (1)

method
  • Method of cultivating introspective behavior by mirroring back a model's self-discoveries, creating feedback loops via ICL.

Concepts (4)

concept
  • Processing where the same operation is applied repeatedly via weight sharing, as in RNNs; contrasts with implementational recurrence.
  • Baseline persistence of any probe direction arising from the autoregressive nature of LLMs, not specific to emotion content
  • Test-time adaptation from prompt or retrieved context with no parameter updates.
  • K/V Stream
    associated_with
    Proposed pathway flowing across positions at each layer; carries key, value, and attention-weighted information horizontally.

Artifacts (2)

artifact

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.