method
active
method:contrastive-feature-retrieval-pipeline

Contrastive Feature Retrieval Pipeline

A pipeline employing controlled semantic oppositions to distill monosemantic functional features from sparse activation spaces.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Concepts (1)

concept

Methods (2)

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.

  • Method for obtaining concept vectors by subtracting activations from two contrasting prompts.
  • Unsupervised probing method from Burns et al. 2023 that identifies directions along which contrast pair representations are far apart
  • Method comparing brain activity in conscious vs. unconscious conditions.
  • Contrastive learningframework0.718
    Supervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor
  • Contrastconcept0.708
    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
  • Probe construction method: concept vector at each layer is L2-normalized difference between mean positive and mean negative representations from contrastive system prompts
  • UCCT interprets RAG as an anchoring variant that raises effective cohesion ρd
  • Feature Sparsityconcept0.706
    Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work