finding
active
finding:predictive-component-s-attention-maps-are-low-rank-rank-bottleneck-constrained-tfas-achieve-similar-reconstruction

Predictive component's attention maps are low-rank; rank-bottleneck constrained TFAs achieve similar reconstruction.

Fig. 13.

Source paper

extracted_from
Priors in Time: Missing Inductive Biases for Language Model Interpretability
(2025) · Lubana, Ekdeep Singh · Rager, Can · Hindupur, Sai Sumedh R. · Costa, Valerie +12

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Alternative sparsity notion proposed for predictive component.

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.