afterless

🧵1/6 SAEs have become a staple of LLM interpretability, but what if we applied them to image generation models? My recent paper with @dmhook, @Yixiong_Hao, @afterlxss, @Sheikheddy, and @ArthurConmy adapts SAEs to understand the SOTA diffusion transformer FLUX.1 ⬇️

@neverrixx @dmhook @Yixiong_Hao @Sheikheddy @ArthurConmy Absolute fun project to work on, great thread as well, looking forward to potential future collaborations.

1/8 🧵 Did you know that it’s possible to steer LLM behavior at each token on the fly? Excited to share my recent #ICLR2025 workshop paper in collaboration with @afterlxss, @neverrixx, and @Sheikheddy (many, many thanks😆) Paper: arxiv.org/abs/2505.03189 Poster (TLDR): tinyurl.com/caeposter