concept
active
concept:representational-familiarityRepresentational familiarity
How familiar a model is with a numeral system, manipulated via bases in Experiment 2.
Neighborhood — ranked by edge-count
Methods (1)
method
- Quantitative study varying representational familiarity via numeral bases B10/B8/B9 at fixed computational complexity
Concepts (3)
concept
- Base-10 arithmeticassociated_withHigh pretraining exposure numeral system used in E2.
- Base-8 arithmeticassociated_withModerate pretraining exposure numeral system used in E2.
- Base-9 arithmeticassociated_withLow pretraining exposure numeral system used in E2.
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.
- Property of conscious representations: they do not contain information about the fact that they are representations at the level of the representation itself
- The central empirical phenomenon: different neural networks trained on different data/objectives develop increasingly similar representations
- Measure of similarity between the similarity structures (kernels) induced by two different representations
- Core phenomenon studied: when causal interventions shift internal representations away from the natural distribution
- The proposed domain-general property indexed by deception features that governs both factual accuracy and experiential self-report
- Distance between prior and target representations.
- The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.
- One-dimensional curved surface in internal activation space; the paper demonstrates alignment with behavior manifold.