Neural Geometry Framework

Conceptual scheme introduced in this paper: neural networks develop internal geometric representations that mirror real-world geometry, providing the right level of description for interpretability and control.

Neighborhood — ranked by edge-count

Papers (1)

paper

The World Inside Neural Networks
introduces

Concepts (2)

concept

manifold
cites
A smooth, potentially curved surface in activation space along which activations vary according to a coherent semantic dimension.
geometrically-true objects
cites
Proposed interpretability primitives that respect the geometric structure of representations, as opposed to atomized SAE features.

Communities (1)

community

Neural Geometry
cites

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.

neural behavior geometryconcept0.860
The manifold structure of model outputs, modelled by M_y.
Neural Representation Geometryconcept0.840
The broader conceptual framework that neural activations exhibit non-Euclidean geometric structure causally linked to behavior.
Neural Geometriesconcept0.816
Geometry unifies diverse neural architectures in machine learning systems.claim0.782
Geometry-Aware Steering Frameworkframework0.777
The overarching theoretical framework proposed in the paper, asserting that steering interventions should be aligned with the geometric structure of the model's representation manifold.
Neural codeconcept0.762
The model's parameters considered as the actual 'code' implementing its algorithms, as opposed to human-written code.
Geometryconcept0.757
The actual shapes and spatial relationships of buildings, essential to living structure.
Neural Annealingframework0.756
Michael Johnson's prior work on how neural networks (and brains) can be 'annealed' to find optimal states.