concept
active
concept:representation-based-pathRepresentation-based Path
The path in activation space derived by fitting the representation manifold, used to steer along the geometric structure of internal representations.
Neighborhood — ranked by edge-count
Concepts (2)
concept
- representation manifoldassociated_withOne-dimensional curved surface in internal activation space; the paper demonstrates alignment with behavior manifold.
- Behavior-based Pathanalogous_toThe path in activation space derived by optimizing steering interventions to produce outputs along the behavior manifold, independent of representation geometry.
Findings (1)
finding
- Key empirical result showing that optimizing for behavioral outputs and fitting representation geometry produce the same path in activation space.
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.
- The idea that features are encoded as directions in activation space.
- The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.
- Sequences of transformations in configuration space that maintain wholeness and reliably lead to living configurations.
- The central question of whether representational geometry implies corresponding computational structure
- Property of conscious representations: they do not contain information about the fact that they are representations at the level of the representation itself
- Measure of similarity between the similarity structures (kernels) induced by two different representations
- The core analytical technique of expanding transformer computations from layer-by-layer products into sums of end-to-end path terms for independent analysis
- Idea that information is spread across many neurons; superposition is a subtype.