finding
active
finding:k-sparse-probing-gives-limited-differentiation-all-saes-outperform-residual-channel-probing-baseline-0-65-on-gemma-2-2b-layer-12

K-sparse probing gives limited differentiation; all SAEs outperform residual-channel probing baseline (0.65) on Gemma-2-2B layer 12

Probing limited.

Source paper

extracted_from
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
(2025) · Adam Karvonen · Can Rager · Johnny Lin · Curt Tigges +11

Neighborhood — ranked by edge-count

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.