finding

active

finding:manifold-geometry-principles-extend-to-months-letters-ages-and-in-context-learning-tasks-across-modalities

manifold geometry principles extend to months, letters, ages, and in-context learning tasks across modalities

Evidence that the weekday cyclic structure is not anomalous but reflects broader principle of concept geometry.

Source paper

extracted_from

Steering Along Manifolds to Control Neural Networks

Neighborhood — ranked by edge-count

Papers (1)

paper

Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
supports

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.
Manifold isometry between representations and behavior
members_of
Neural network activation and behavior manifolds maintain geometric correspondence, enabling intervention optimization across language models and vision tasks.

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.

Analogous alignment between representation manifold and behavior manifold is found across months, letters, ages, and synthetic in-context learning tasks in language models.finding0.832
Generalization finding from the full paper extending beyond days-of-week to other structured concepts.
Manifold geometry provides a practical blueprint for steering model behavior across diverse tasks and modalities.hypothesis0.823
The generalizing predictive claim that manifold steering is a broadly applicable framework beyond the days-of-week case study.
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.claim0.809
The paper's generalization claim, asserting that the days-of-week finding scales to other cyclic and structured concepts.
Manifold geometry provides a practical steering blueprint in an image-action model predicting car position on a hill, extending results across modalities.finding0.807
Cross-modality result from the full paper demonstrating that representation-behavior geometry alignment is not limited to language models.
Manifold steering (Wurgaft et al) will become the standard framework for operationalizing concept-space design in mechanistic interpretability within 18 months.prediction0.796
manifold learningframework0.795
Technique used to fit M_h and M_y from data; enables manifold steering.
Curved manifolds often represent concepts better than linear directions.claim0.790
Proposes that nonlinear geometric structure is superior to linear feature spaces for capturing semantic content.
Representation geometry causally shapes behavior; activation and behavior manifolds are approximately isometric.claim0.762