concept
active
concept:contrastive-stimulus-design

Contrastive Stimulus Design

LAT methodology step constructing paired prompts that elicit divergent behaviors to extract steering vectors

Neighborhood — ranked by edge-count

Methods (1)

method

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.

  • Contrastive Pairsconcept0.783
    Pairs of prompts at different reflection levels used to compute steering vectors.
  • Contrastconcept0.782
    The property that living structures contain intense contrast—far more than one imagines helpful; true opposites which annihilate each other when superimposed, creating differentiation that gives birth to something; contrast unifies rather than separates when used correctly
  • Contrastive learningframework0.768
    Supervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor
  • Method comparing brain activity in conscious vs. unconscious conditions.
  • Contrast Pairsconcept0.735
    Pairs of statements with opposite truth values used as input to CCS; e.g., cities and neg_cities paired statements
  • Core technique: takes mean difference of model activations on contrastive prompts and adds the resulting vector to the residual stream at inference time.
  • Probe construction method: concept vector at each layer is L2-normalized difference between mean positive and mean negative representations from contrastive system prompts
  • Unsupervised probing method from Burns et al. 2023 that identifies directions along which contrast pair representations are far apart