The paper identifies stable regions in Transformers' residual streams, showing insensitivity to small changes but high sensitivity at boundaries, aligning with semantic distinctions and clustering similar prompts.

https://arxiv.org/abs//2409.17113

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers