covariance-geometry-unifies-analysis-and-editing
OUT derived (depth 2)
Created 2026-08-25T03:02:14+00:00 · Reviewed 2026-08-25T04:28:09+00:00
The mathematically principled framework for both interpreting (SAE feature extraction, Park polytope analysis) and modifying (ROME rank-one edits) LLM representations is second-moment covariance geometry applied to the residual stream, since C = KKᵀ whitening defines the canonical coordinate system in which all three operations become linear algebra on the same substrate.
Justifications
SL — The universality of the residual-stream substrate provides the *where*; the covariance-geometry canonical tool provides the *how*. Neither suffices alone: without universality the geometry is model-specific; without the canonical tool the substrate has no principled coordinate system. Their conjunction yields a unified algebraic framework.
Antecedents (all must be IN):
- OUT residual-stream-universal-substrate — SAE (middle-layer residual stream), ROME (mid-layer MLP value projection), and Park (final-layer unembedding) all identify the residual stream at different depths as the primary locus of interpretable geometric structure.
- IN covariance-geometry-as-canonical-tool — Independent lines of work (ROME's key-space projection and Park's unembedding whitening) converge on using empirical second-moment matrices to define the "correct" inner product for reasoning about transformer representations.
Dependents
These beliefs depend on this one:
- OUT covariance-geometry-as-operational-semantic-space — The covariance/whitening geometry (second-moment matrices) is the operational definition of semantic coordinate space in LLMs: it simultaneously parameterises feature interpretation (SAE decoder space, Park polytopes), similarity evaluation (cosine→Spearman pipeline), and knowledge modification (ROME rank-one updates), and this structure converges across model families.
- OUT geometric-editing-addressability-bound — The covariance-geometry framework defines a precise and minimal addressable space for knowledge editing (rank-one updates to a single MLP value projection), but the combination of superposition and distributed corpus acquisition structurally bounds this to single-fact local corrections—edits cannot create novel multi-hop associations because the target knowledge was never locally consolidated in the first place.
- OUT knowledge-lifecycle-closed-loop — The full knowledge lifecycle in LLMs—distributed corpus acquisition → local MLP key-value storage → parametric recall → rank-one editing correction—forms a closed loop unified by the covariance geometry, where each stage is addressable in the same second-moment coordinate space.
- OUT local-mlp-editing-principle — The MLP-as-key-value-memory structure provides a principled, minimal-intervention editing mechanism for locally-stored factual (entity-relation-object) associations, with the edit's efficacy and specificity guaranteed by the rank-one update's geometric isolation in the covariance-projected key space.