EPISODE · Nov 19, 2024 · 24 MIN
Steering Language Model Refusal with Sparse Autoencoders
from Arxiv Papers · host Igor Melnyk
The paper explores using sparse autoencoders to steer language model activations for safer responses, improving refusal behavior while noting potential negative impacts on overall performance. https://arxiv.org/abs//2411.11296 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
Embed this episode
Ready to play
Steering Language Model Refusal with Sparse Autoencoders
No transcript for this episode yet
Similar Episodes
No similar episodes found.