geometrically-true objects

Proposed interpretability primitives that respect the geometric structure of representations, as opposed to atomized SAE features.

Neighborhood — ranked by edge-count

framework

Neural Geometry Framework
cites
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.

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.

Geometryconcept0.803
The actual shapes and spatial relationships of buildings, essential to living structure.
real-world geometryconcept0.782
The structured geometry present in the external world (e.g., circles, spatial manifolds) that networks learn to mirror.
Geometry of featuresconcept0.763
Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
geometric engineconcept0.747
The underlying geometric structure in a work that actually produces the felt feeling; a concrete configuration that generates the intended emotional quality.
Sequential Geometryconcept0.744
A geometric structure characterizing sequential reasoning task representations, used as a test case for manifold steering
Rectangle as universal objectconcept0.735
Every element (text, spreadsheet cell, graphic, paragraph) is fundamentally a rectangle with value and appearance rules; unifies the system conceptually.
Differentiation as geometric generationconcept0.731
The process through which form is created by successive differentiating operations, not by adding parts.
positive geometric characterconcept0.726
The quality of space that is shaped, contained, and composed of distinct centers, feeling as solid as a carved object.