finding
active
finding:systematic-skew-toward-larger-neuron-contributions-in-spd-2-layer-model-unexplainedSystematic skew toward larger neuron contributions in SPD 2-layer model, unexplained
Figure 10 discrepancy.
Source paper
extracted_from(2025) · Lucius Bushnaq · Dan Braun · Lee Sharkey
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central claim.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Neuron contributions of SPD subcomponents closely match target model across all 100 featuresfinding0.827Figure 7.
- SPD finds 100 W_in components and a single rank-50 W_out component spanning both layers in the 2-layer modelfinding0.794Multi-layer mechanisms.
- ReLU hidden layer model (n=10, m=5) shifts from monosemantic to polysemantic neurons as sparsity increasesfinding0.773Neuron-level phase change.
- Fundamental assertion: single imperative (free energy minimization) explains diverse cognitive and neural phenomena.
- Key limitation of the paper's approach; MLP layers make up 2/3 of standard transformer parameters
- Load-bearing theoretical claim providing the conceptual foundation for DAS.
- Data-induced competition over resources.
- Core testable hypothesis of UCCT about the nature of performance transitions under anchoring