Representation and computation can diverge; cyclic geometry is representational invariant while operations use generic substrate.

Neighborhood — ranked by edge-count

Communities (3)

community

Manifold-aware concept steering in neural representations
members_of
Explores geometry of activation/behavior manifolds to enable selective, non-destructive concept interventions.
Geometric concept representations in neural networks
members_of
Concepts encoded as curved manifolds and circular structures in LLM activation spaces.
Neural geometry as fundamental computational substrate
members_of
Geometric structure in neural representations causally determines computation and behavior across diverse architectures, revealed through analysis of learned manifolds and cyclic concepts.

Vectors (1)

vector

Convergent Representations
addresses_vector

Source docs (1)

source_doc

2026-05-14_phil-trans-A-goodfire-aboutblank-impact.md
extracted_from

Related by similarity (8)

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.

Representation-computation mismatch (Feucht: cyclic concepts computed in base-10, not circular geometry) will force About Blank to decouple 'representational geometry' from 'operational structure' in prediction0.815
There is a bidirectional relationship between the geometry of representation and behavior across tasks and modalities.claim0.795
Author’s interpretive claim that the shared geometry is general and robust.
Neural networks compute cyclic concepts in generic substrate machinery (base-10 addition) not naturally cyclic computation.claim0.789
Language models prefer reusing generic arithmetic mechanisms over learning task-specific modular computations even when task-specific geometry existsclaim0.788
Broader interpretive claim about LM learning bias inferred from the findings
The alignment between representation geometry and behavior geometry is not limited to days of the week but extends to months, letters, ages, and synthetic in-context learning tasks.claim0.788
The paper's generalization claim, asserting that the days-of-week finding scales to other cyclic and structured concepts.
There is a clear bidirectional relationship between the geometry of behavior and representation: steering along representation manifolds follows behavior manifolds, and vice versa.claim0.786
The paper's finding that the alignment holds in both directions — from representation to behavior and from behavior back to representation space.
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.786
Conceptual geometry is consistent across representation space and behavior space.claim0.784
Interpretive assertion: the same geometric structure (e.g. circular for days) appears identically in both internal activations and output probabilities.