concept
active
concept:real-world-geometryreal-world geometry
The structured geometry present in the external world (e.g., circles, spatial manifolds) that networks learn to mirror.
Neighborhood — ranked by edge-count
Claims (1)
claim
- Core claim of the paper: the right level of description for neural representations is geometric structure mirroring the world.
Concepts (1)
concept
- Geometryrelated_toThe actual shapes and spatial relationships of buildings, essential to living structure.
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.
- A more complex geometric structure used to characterize in-context learning task representations
- Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
- The spatial/geometric organization of conceptual structure within neural network representations; central to the paper's thesis.
- Proposed interpretability primitives that respect the geometric structure of representations, as opposed to atomized SAE features.
- A method of using existing, similar streets or places to simulate and judge the dimensions and qualities of a proposed space by standing there, using markers, and walking through.
- A geometric structure characterizing sequential reasoning task representations, used as a test case for manifold steering
- Dynamic model connecting logic to geometry through explicit treatment of information flow and interaction; demonstrates emergent logical complexity from simple copy-cat processes.
- The geometry corresponding to physical dynamics, instantiated in the video world model test domain