Progress measures for grokking via mechanistic interpretability#Machine Learning#Interpretability#Paper#PDF#Explainability#Deep Learning·arxiv.org·Feb 5, 2023Progress measures for grokking via mechanistic interpretability
Will You Find These Shortcuts?#Machine Learning#Model#Integrity#Google Research#Interpretability·ai.googleblog.com·Dec 11, 2022Will You Find These Shortcuts?