claim
active
claim:networks-compute-on-geometric-manifolds-and-control-should-respect-that-geometryNetworks compute on geometric manifolds and control should respect that geometry.
Strong interpretive assertion linking discovery and control: neural computation is fundamentally manifold-structured.
Neighborhood — ranked by edge-count
Communities (3)
community
- Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
- Concepts encoded as curved manifolds and circular structures in LLM activation spaces.
- Geometric structure in neural representations causally determines computation and behavior across diverse architectures, revealed through analysis of learned manifolds and cyclic concepts.
Concepts (1)
concept
- Manifold SteeringgatesCentral framework: steering neural networks by intervening along the curved manifold where a concept lives, rather than in straight lines through 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.
- Mechanistic explanation: geometric structure emerges naturally from standard training on data with underlying structure.
- The opening statement of the paper, framing concept geometry as the key to neural network control.
- Core claim of the paper: the right level of description for neural representations is geometric structure mirroring the world.
- Manifold geometry provides a practical blueprint for steering model behavior across diverse tasks and modalities.hypothesis0.777The generalizing predictive claim that manifold steering is a broadly applicable framework beyond the days-of-week case study.
- Neural representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.764Central hypothesis tested via manifold steering experiments across language models and video world models.