Papers and Projects - Josh Engels

Publications on mechanistic interpretability and AI Safety.

Papers Paper | Blog | Twitter Janos Kramar, Joshua Engels, Zhengxuan Wang, Bilal Chughtai, Rohin Shah, Neel Nanda, and Arthur Conmy.Paper | Twitter Reilly Haskins, Bilal Chughtai, and Joshua Engels.Paper | Blog | Twitter Daria Ivanova, Riya Tyagi, Joshua Engels, and Neel Nanda.Paper | Blog Aria Wong, Joshua Engels, and Neel Nanda.Paper | Blog Joshua Engels*, David Baek*, Subhash Kantamneni*, and Max Tegmark.Paper | Code | Twitter Subhash Kantamneni*, Joshua Engels*, Senthooran Rajamanoharan, Max Tegmark, and Neel Nanda.Paper | Blog | Code | Twitter Mathew Chen*, Joshua Engels*, and…

saved by

• Ishaan Panigrahi

related reading

• Dylan Samdsam99.github.io
• Josh Engels on X: "New GDM interp research: SFT is a big deal for safety relevant behaviors. We recently investigated root causes for some of Gemini’s behaviors. We were surprised to find that many behaviors actually came from the initial supervised finetuning stage, not later stages like RL! 🧵 https://t.co/mLg87XuXK5" / Xx.com
• Transformer Circuits Threadtransformer-circuits.pub
• Getting Caught Up to Modern LLM Research | Samarth Goeldev.samarthgoel.com
• Trending Papers - Hugging Facepaperswithcode.com
• Aman's AI Journal • Primers • Ilya Sutskever's Top 30aman.ai
• Publicationseilab.gatech.edu
• Noah Shinnnoahshinn.com
• The 2025 AI Engineering Reading List - Latent.Spacelatent.space
• An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
• Paper Feeddavisrbrown.com
• Eric Jangevjang.com