ArchiveSequencesAbout

QuestionsEventsShortformAlignment ForumAF Comments

HomeFeaturedAllTagsRecent Comments

Am8ryllis

Karma: 22

AllPostsComments

Sparse trinary weighted RNNs as a path to better language model interpretability

Am8ryllis17 Sep 2022 19:48 UTC

19 points

13 comments3 min readLW link