Euclidean geometry assumption in steering

Linear steering implicitly assumes a flat, Euclidean activation space, leading to off-manifold excursions.

Neighborhood — ranked by edge-count

method

linear steering
implements
Typical approach that adds a scaled steering vector to representations; the paper argues this is mismatched with actual representation geometry.

concept

Euclidean Geometry Assumption
related_to
The implicit assumption of linear steering methods, which the paper argues is inappropriate for neural activation spaces

finding

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.

geometry-based steeringconcept0.821
Paradigm of finding the right geometry (manifold) for principled control.
Gap: linear steering assumes Euclidean geometry and does not account for the actual curved geometry of activation manifoldsconcept0.813
The research gap that motivates manifold steering as an alternative to conventional linear approaches
Optimally steering model behavior requires isolating concept geometry and defining operators to navigate it.claim0.758
Linear steering is often mismatched with a model's internal representation geometry, producing noisy, off-target effects.claim0.754
The paper's critique of the standard linear steering baseline, supported by the days-of-week demo.
Steering along manifolds provides better control than linear steering when the concept geometry is non-linear.claim0.754
The central thesis of the paper, motivating the shift from linear to geometry-aware manifold steering.
The core problem of steering should be recast from finding the right direction to finding the right geometryclaim0.753
The paper's programmatic conclusion about how the field should reconceptualize neural network steering
Geometry-Aware Steering Frameworkframework0.748
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.
direction-based steeringconcept0.747
Paradigm of finding the right direction in activation space (e.g., linear steering).