concept
active
concept:cross-layer-superposition

Cross-layer superposition

Representation of features spread across multiple layers, complicating dictionary learning.

Neighborhood — ranked by edge-count

Thinkers (1)

thinker
  • Yun et al.
    studies
    First to track unsupervised features across layers with a single dictionary.

Frameworks (1)

framework
  • Core theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition

Methods (1)

method
  • Sparse dictionary learning variant that reads and writes to multiple layers or models, yielding shared features.

Concepts (1)

concept
  • Phenomenon where models represent more features than dimensions via almost-orthogonal directions.

Hypotheses (1)

hypothesis

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.