claim
active
claim:language-models-do-not-reproduce-the-full-architecture-of-global-workspace-theory-they-share-functional-but-only-some-architectural-propertiesLanguage models do not reproduce the full architecture of global workspace theory; they share functional but only some architectural properties.
Explicit hedge.
Source paper
extracted_fromAuthors
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central thesis.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Language models able to generate images could develop a visual component of their workspace.hypothesis0.832Prediction from verbal-output account.
- Dissociation.
- Opening sentence setting the stage for the importance of interpretability.
- Broader interpretive claim about LM learning bias inferred from the findings
- The workspace may be verbalizable because the model's output space and input space are verbal.claim0.797Speculative explanation.
- Core empirical hypothesis of the paper, supported by successful VPD decomposition yielding ~10,000 interpretable subcomponents across 24 weight matrices.
- Articulates why a one-layer transformer with MLP is the appropriate starting target for mechanistic interpretability