question
active
question:how-does-the-workspace-emerge-with-model-size-and-pretraining-timeHow does the workspace emerge with model size and pretraining time?
Open question.
Source paper
extracted_fromAuthors
Neighborhood — ranked by edge-count
Papers (1)
paper
- Verbalizable Representations Form a Global Workspace in Language Modelsassociated_withmentions
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.
- Core goal statement.
- Dissociation.
- First research question driving the study of early persona vector formation
- Language models able to generate images could develop a visual component of their workspace.hypothesis0.759Prediction from verbal-output account.
- The workspace may be verbalizable because the model's output space and input space are verbal.claim0.741Speculative explanation.
- Directed modulation.
- Core framing.
- DAS finds causal effect at all training timesteps including when model is just initialisedfinding0.736Corroborates Wu et al. 2023 finding that DAS expressivity inflates causal effect estimates