Interpretability Courses and Certifications

UofU Data Science

Interpretability of LLMs - Evaluating SAE Feature Descriptions

Explore methods for evaluating Sparse Autoencoder feature descriptions in large language models through practical interpretability techniques.

• YouTube
• 1 hour 12 minutes
• On-Demand
• Free Video

UofU Data Science

Model Diffing with Crosscoders - CS 6966 Interpretability of LLMs Spring 2026

Explore model diffing techniques using crosscoders to understand differences between large language models and enhance interpretability methods.

• YouTube
• 44 minutes
• On-Demand
• Free Video

UofU Data Science

Utah CS 6966 Interpretability of LLMs - Probing Part 2 - Spring 2026

Delve into advanced probing techniques for understanding how large language models process and represent information internally.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Responsible AI for Developers: Interpretability & Transparency

Explore practical methods and tools to achieve interpretability and transparency in both data and AI models.

• edX
• 3 weeks, 3-4 hours a week
• On-Demand
• Free Online Course (Audit)

Yannic Kilcher

On the Biology of a Large Language Model - Part 2

Delve into the internal mechanisms of Claude 3.5 Haiku as Yannic Kilcher explores Anthropic's Transformer Circuit Blog Post, examining how this lightweight production model functions across various contexts.

• YouTube
• 56 minutes
• On-Demand
• Free Video

Optimizing for Interpretability in Deep Neural Networks - Mike Wu

Explore techniques for making deep neural networks more interpretable through regularization, focusing on medical applications in critical care and HIV treatment. Insights on balancing model performance with human-understandable decision processes.

• YouTube
• 51 minutes
• On-Demand
• Free Video

Valence Labs

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models

Explore causal abstraction theory for uncovering and inducing interpretable structures in deep learning models, focusing on faithful explanations and interventions during analysis and training.

• YouTube
• 56 minutes
• On-Demand
• Free Video

Simons Institute

Towards Interpretable Data Science

Explore holistic approaches to interpretable data science, focusing on counterfactual and attribution-based explanations for complex data processing and decision support systems.

• YouTube
• 35 minutes
• On-Demand
• Free Video

UofU Data Science

Attribution Graphs - Edge Weights and Pruning

Explore edge weights and automatic extraction of sparse feature circuits in large language models through attribution graph analysis and pruning techniques.

• YouTube
• 1 hour 9 minutes
• On-Demand
• Free Video

GERAD Research Center

Operational Research for Fairness, Privacy and Interpretability in Machine Learning

Explore responsible AI through operational research, focusing on fairness, interpretability, and privacy in machine learning. Learn to leverage Integer Linear Programming for optimal, fair rule lists.

• YouTube
• 45 minutes
• On-Demand
• Free Video

Computational Genomics Summer Institute CGSI

Interpretability and Out-of-Distribution Generalization in Deep Predictive Models

Explore interpretability and out-of-distribution generalization in deep predictive models, focusing on nuisance-induced spurious correlations and real-time Shapley value estimation techniques.

• YouTube
• 41 minutes
• On-Demand
• Free Video

Institute for Pure & Applied Mathematics (IPAM)

Interpretability for Deep Learning: Theory, Applications and Scientific Insights

Dive into deep learning interpretability, exploring methods to enhance transparency, safety, and trustworthiness in AI deployment while uncovering scientific insights in various domains.

• YouTube
• 56 minutes
• On-Demand
• Free Video

Center for Language & Speech Processing(CLSP), JHU

Deep Learning Interpretability and Explainability of Speech in a Clinical Context

Explore deep learning interpretability and explainability of speech in clinical settings, focusing on advanced techniques and their practical applications.

• YouTube
• 54 minutes
• On-Demand
• Free Video

NPTEL-NOC IITM

Responsible AI: Capabilities, Bias, Interpretability, and Alignment - Part 1

Explore responsible AI concepts including capabilities, bias, interpretability, explainability, RLHF, alignment, and potential risks.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Simons Institute

A Multimodal Automated Interpretability Agent - Understanding Lower-Level Intelligence

Explore a multimodal AI agent for automated interpretability, bridging AI, psychology, and neuroscience to understand lower-level intelligence.

• YouTube
• 35 minutes
• On-Demand
• Free Video