YoVDO

Towards Monosemanticity: Decomposing Language Models with Dictionary Learning

Offered By: Unify via YouTube

Tags

Language Models Courses Neural Networks Courses Feature Extraction Courses Interpretability Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore a comprehensive presentation on "Towards Monosemanticity: Decomposing Language Models With Dictionary Learning" from Anthropic's research team. Delve into the concept of polysemanticity in neural networks and learn how sparse autoencoders can extract more interpretable, monosemantic features. Discover how this approach enhances understanding of language model behavior compared to analyzing original polysemantic neurons. Gain insights into the latest advancements in AI research, including techniques for improving model interpretability and reasoning. Connect with additional resources such as The Deep Dive newsletter and Unify's blog for further exploration of AI deployment and industry trends. Engage with the AI community through various social media platforms and join discussions on cutting-edge developments in machine learning, deep learning, and natural language processing.

Syllabus

Towards Monosemanticity Explained


Taught by

Unify

Related Courses

Machine Learning Modeling Pipelines in Production
DeepLearning.AI via Coursera
Live Responsible AI Dashboard: One-Stop Shop for Operationalizing RAI in Practice - Episode 43
Microsoft via YouTube
Build Responsible AI Using Error Analysis Toolkit
Microsoft via YouTube
Neural Networks Are Decision Trees - With Alexander Mattick
Yannic Kilcher via YouTube
Interpretable Explanations of Black Boxes by Meaningful Perturbation - CAP6412 Spring 2021
University of Central Florida via YouTube