Skip to article frontmatterSkip to article content
Site not loading correctly?

This may be due to an incorrect BASE_URL configuration. See the MyST Documentation for reference.

Introduction to Interpretability for Language Models

In this two-week crash course, participants will gain a baseline understanding of the vocabulary, concepts, and methods involved in current interpretability work. Our first week overviews the basic components of generative language models like GPT-2. The second week ferries participants through a variety of approaches that researchers use to explain model behavior, ending with a day on multimodality. Throughout, our focus will be on the model as an object in its own right. Instead of using a model to analyze some external dataset, our hands-on sessions select various facets of the model itself (embeddings, outputs, etc.) and build explanations on that basis.

Syllabus

The course runs Monday through Thursday, 10am-1pm EST from July 20-30.

DayDateTopic
1M (7/20)Setup and overview
2T (7/21)Tokenization and embeddings
3W (7/22)Embeddings and attention
4R (7/23)Sampling and generation
5M (7/27)Text as data
6T (7/28)Attribution and feature importance
7W (7/29)Meta-modeling
8R (7/30)TBD: Participants decide

Prerequisites

This course is intended to be a general introduction and makes no assumptions about participant backgrounds (familiarity with programming, experience in natural language processing, etc.). It will walk participants through everything they need to know to complete each session.