What You Need to Know Before
You Start

Starts 15 July 2026 08:40

Ends 15 July 2026

00 Days
00 Hours
00 Minutes
00 Seconds
course image

Interpretability of LLMs - Generating SAE Feature Descriptions - Spring 2026

Explore advanced techniques for generating Sparse Autoencoder feature descriptions to enhance Large Language Model interpretability and transparency.
UofU Data Science via YouTube

UofU Data Science

6095 Courses


1 hour 12 minutes

Optional upgrade avallable

Not Specified

Progress at your own speed

Free Video

Optional upgrade avallable

Overview

Explore advanced techniques for generating Sparse Autoencoder feature descriptions to enhance Large Language Model interpretability and transparency.


Subjects

Computer Science