Natural Distribution of Representations

The distribution of latent representations produced by the model under unperturbed inputs

Neighborhood — ranked by edge-count

concept

Representational Divergence
associated_with
Core phenomenon studied: when causal interventions shift internal representations away from the natural distribution

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.

Structure in representationsconcept0.803
The central question of whether representational geometry implies corresponding computational structure
Distributed representationconcept0.802
Idea that information is spread across many neurons; superposition is a subtype.
Linear representationconcept0.791
The idea that features are encoded as directions in activation space.
Higher-Order Representationsconcept0.781
Representations of one's own mental states; associated with consciousness in higher-order theories.
Distributed Neural Representationsconcept0.775
Representations where individual neurons play multiple conceptual roles; patterns consisting of linear combinations of unit vectors.
Categorical Distributionconcept0.772
Probability distribution over discrete states or outcomes.
Non-Linear Representation Dilemmaconcept0.768
Core contribution: the impasse where lifting linearity in alignment maps makes causal abstraction vacuous, but keeping it may miss non-linearly encoded features
Representational dynamicsconcept0.765
The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.