concept
active
concept:autoregressive-persistence

autoregressive persistence

Baseline persistence of any probe direction arising from the autoregressive nature of LLMs, not specific to emotion content

Neighborhood — ranked by edge-count

Methods (1)

method
  • Controls for variance by sampling random directions from top-k PC spaces matching each emotion probe's explained variance, and subtracting median persistence of 20 matched directions

Concepts (2)

concept
  • Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
  • Emotion feature persistence above and beyond the persistence expected from high variance explained alone, computed by subtracting median variance-matched probe persistence

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.