concept
active
concept:skip-trigram

Skip-Trigram

A three-token pattern of the form [source]...[destination][out] that one-layer attention heads implement; the paper's key characterization of one-layer transformer behavior

Neighborhood — ranked by edge-count

Concepts (5)

concept
  • Model failures where a one-layer attention head must simultaneously increase probability of unintended token combinations because it factors the three-way interaction
  • Test-time adaptation from prompt or retrieved context with no parameter updates.
  • Mechanistic circuits in transformers documented by Olsson et al. 2022, cited as evidence for pattern-repository assumption
  • The first toy model analyzed; shown to implement an ensemble of bigram and skip-trigram models readable directly from weights
  • Next-token probabilities conditioned only on the present token; what zero-layer transformers optimally approximate and what the direct path W_U W_E contributes to in all transformers

Related by similarity (6)

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.

  • Trigram Featuresconcept0.758
    Features implementing specific three-token sequence predictions (e.g., predicting '19' after 'COVID-')
  • causal bypassingconcept0.694
    Confound where naming injected concepts reflects direct logit effects rather than metacognitive awareness, raised by Morris & Plunkett
  • Shadowmethod0.667
    Attribute: exposing latent tendencies of a text, what isn't said but could be, a haunting presence.
  • Proposed constitutional article defining mindful reflection steps in CCAI implementation
  • ReActframework0.657
    Prior framework for synergizing reasoning and acting in LLM agents, foundational to agent harness concept
  • Gradient Descentmethod0.655
    Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data