concept
active
concept:virtual-weights

Virtual Weights

Implicit weights directly connecting any pair of layers computed by multiplying output weights of one layer with input weights of another through the residual stream

Neighborhood — ranked by edge-count

Claims (1)

claim

Concepts (1)

concept
  • Residual Stream
    associated_with
    Proposed pathway flowing through layers at each position; calculates K/V values that feed horizontal information flow.

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.

  • virtual governorconcept0.728
    A high-level control node (e.g., calcium pattern, resting potential) that is a complex function of many low-level components, not 1:1 mappable to genes.
  • Virtual Machineconcept0.715
    A computing layer above physical hardware; Sloman uses this as an analogy for mental processes not reducible to physics.
  • Task weightconcept0.711
    Coefficient weighting each task loss in the MTL objective.
  • Weight Editingmethod0.708
    Editing network weights to test predictions about circuit function; proposed as falsifiability test for circuit claims
  • Logit weight contributions from a feature that arise due to superposition with other features, not from the feature's own causal role
  • V valuesconcept0.702
    In attention, value vectors that carry the information future positions should receive.
  • Load-bearing claim about the tractability of circuit analysis; central thesis of Claim 2
  • Equal Weightingframework0.694
    Baseline MTL approach minimizing sum of task losses with equal weights; suffers from task balancing