Low-Level Analysis of an LLM

​NOTE: Time has now been set! Location will definitely be in Manhattan Chinatown. Exact building number will come soon!

Ever wonder how transformers actually do some of their computation? Wanted to know more about what this "mechanistic interpretability" thing is and how it relates to AI safety? This is the workshop for you!

​Please see https://aisafetyawarenessfoundation.org/workshops/nyc-dec-2024-2/ for more details.