Are we interpreting the model of interest?
Comments
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules
Summary
A blog post by an interpretability researcher reports that enabling output_attentions=True silently switched a vision-language model from SDPA to eager attention, cutting benchmark accuracy from about 70% to 20%.