quote

active

quote:concept-geometry-provides-a-blueprint-for-controlling-the-behavior-of-neural-networks-if-you-know-how-to-look

"Concept geometry provides a blueprint for controlling the behavior of neural networks—if you know how to look."

The opening statement of the paper, framing concept geometry as the key to neural network control.

Source paper

extracted_from

Steering Along Manifolds to Control Neural Networks

Neighborhood — ranked by edge-count

Papers (1)

paper

Steering Along Manifolds to Control Neural Networks
introduces

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 representation geometry causally shapes behavior; interventions respecting that geometry will yield natural trajectories.hypothesis0.804
Central hypothesis tested via manifold steering experiments across language models and video world models.
Geometry in neural representation is not merely incidental, but is in fact the proper object for enabling principled control via intervention on internals.claim0.802
Core interpretive assertion: geometric structure is causally load-bearing, not epiphenomenal.
"Representation geometry is a window into the inner world of neural networks."quote0.801
The paper's concluding summary statement asserting the deep interpretive significance of representation geometry.
Networks compute on geometric manifolds and control should respect that geometry.claim0.798
Strong interpretive assertion linking discovery and control: neural computation is fundamentally manifold-structured.
Geometry unifies diverse neural architectures in machine learning systems.claim0.784
The geometry of internal representations and the geometry of model behavior share a precise correspondence — representation geometry is a window into the inner world of neural networks.claim0.781
The paper's deepest interpretive claim, asserting that representation structure and behavioral structure are not coincidentally aligned but deeply connected.
Manifold geometry provides a practical blueprint for steering model behavior across diverse tasks and modalities.hypothesis0.779
The generalizing predictive claim that manifold steering is a broadly applicable framework beyond the days-of-week case study.
Networks encode structured geometric concepts that reflect external reality.claim0.779
Core claim of the paper: the right level of description for neural representations is geometric structure mirroring the world.