Part 2 5 Interpretability

Summary

Neel Nanda discusses mechanistic MIT 6.S897 Machine Learning for Healthcare, Spring 2019 Instructor: Peter Szolovits View the complete course: ... A practical guide to neural nets, superposition, and expts around polysemanticity. Try Explain by Scrimba: ... A small language model was asked where the Eiffel Tower is, and its top answer was London. This course treats that as a service ... More explainability techniques (anchors, counterfactuals, prototypes, influential instances) but also discussions on gaming ... What can we learn about an AI by reading its reasoning—and what stays hidden inside the model? For Episode Language models are increasingly capable of complex reasoning, yet their successes and failures offer only a partial picture of ... This video has been made for teaching use at Northumbria University in England, but has been made publicly available. Manipulating and Measuring Model Speaker: Hanieh Arjmand, ML Researcher, Lydia.ai & Spark Tseung, Applied Data Scientist, Lydia.ai Model Notes: drive.google.com/file/d/10tV6liSjczHd4fp9skGgHJ1EQCioHxWk/view?usp=sharing. 80000hours.org/mlst Visit our sponsor 80000 hours - grab their free career guide and their podcast! Use our ...