concept
active
concept:j-space-verbalisable-workspace

J-space (Verbalisable Workspace)

Gurnee et al.'s privileged set of verbalisable representations behaving as a within-pass global workspace.

Neighborhood — ranked by edge-count

Methods (1)

method
  • Persona Vectors
    associated_with
    Directions in activation space encoding a model's dispositional self-presentation, used as evidence for self-modelling.

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.

  • wordspaceconcept0.814
    The interior domain of the text, the space of inscription.
  • worldspaceconcept0.798
    The exterior domain outside the text block, the surrounding world.
  • White Spaceconcept0.776
    The charged, active areas between and around text elements, differentiating wordspace from worldspace.
  • Positive Spaceconcept0.776
    The property that every bit of space swells outward, is substantial in itself, and is never the leftover from an adjacent shape; every single part of space has positive shape as a center with no amorphous meaningless leftovers
  • Architectural feature integrating information from modules and broadcasting it, associated with consciousness per GWT.
  • Behavior Spaceconcept0.750
    A geometric space of all output token probability distributions, equipped with Hellinger distance, used to visualize model behavior.
  • solid spaceconcept0.748
    Space so positively shaped that it feels almost like a solid, carved volume — the ideal of positive space.
  • Substrate on which causal emergence was computed across agent lifetimes; aligned with learning success.