paper
referenced-only
2009
paper:doi-10-7551-mitpress-9780262170055-001-0001Dataset Shift in Machine Learning
ByJoaquin Quionero-Candela·Masashi Sugiyama·A. Schwaighofer·Neil D. Lawrence
Similar preprints — Semantic Scholar
Cited by (1)
- Understanding and Steering Llama 3 with Sparse Autoencoders - Goodfire
A sparse autoencoder trained on layer-19 residual-stream activations of Llama-3-8B-Instruct, using LMSYS-Chat-1M, yields features that can be labeled automatically, ranked by causal relevance, and use