finding
active
finding:tfa-reaches-nmse-comparable-to-saes-on-gemma-2-2b-e-g-story-0-139-vs-batchtopk-0-152-web-0-139-vs-0-139-while-pred-only-is-worse-0-34-0-38

TFA reaches NMSE comparable to SAEs on Gemma-2-2B (e.g., Story 0.139 vs BatchTopK 0.152; Web 0.139 vs 0.139), while Pred-only is worse (0.34–0.38).

Table 1.

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