superposition-geometry-explains-universality

OUT derived (depth 2)

Created 2026-08-25T03:05:14+00:00 · Reviewed 2026-08-25T04:02:18+00:00

The cross-model universality of feature geometry (SAE features more similar across architectures than within, Park orthogonality validated on both Gemma and LLaMA) is a consequence of superposition: the over-complete compositional basis is determined by the shared semantic grammar of language, making geometric structure an architectural invariant rather than a model-specific artifact.

Justifications

SL — The compositional mechanism (superposition as basis, depth-1) provides the *why*; the observed convergence (depth-1) provides the *that*; together they establish universality as a structural necessity of language composition rather than a training coincidence.

Antecedents (all must be IN):

  • OUT superposition-as-compositional-basis — Superposition is the fundamental compositional mechanism in LLMs: the 10–200× over-complete expansion (SAE), the key-value memory structure (ROME's W_fc/W_proj), and the direct-sum space decomposition (Park's polytope+orthogonality) are three independent geometric consequences of the same over-completeness.
  • IN multi-model-geometric-convergence — Both the polytope/orthogonality geometry (Park, validated on Gemma-2B and LLaMA-3-8B) and sparse feature structure (SAE, universal across architectures) converge on the finding that transformer representation spaces carry model-independent geometric invariants.

Dependents

These beliefs depend on this one: