Media Summary: You can find more information including the the course syllabus and suggested readings at ... CS 7180: Neural Mechanics Spring 2026 Course at Northeastern University Modern AI systems are powerful but opaque: even ... You wouldn't normally fiddle with weights of a state-of-the-art deep network after weeks of training. But why not? In this ECCV ...

David Bau Interpretability And Model - Detailed Analysis & Overview

You can find more information including the the course syllabus and suggested readings at ... CS 7180: Neural Mechanics Spring 2026 Course at Northeastern University Modern AI systems are powerful but opaque: even ... You wouldn't normally fiddle with weights of a state-of-the-art deep network after weeks of training. But why not? In this ECCV ...

Photo Gallery

David Bau: Interpretability and model editing
Introduction to Mechanistic Interpretability with David Bau
David Bau – Resilience and Interpretability
"In Defense of Curiosity" with David Bau (NeurIPS 2025 Mech Interp Workshop)
Neural Mechanics Week 1: LLM Foundations and Logit Lens with David Bau
David Bau - Direct Model Editing and Mechanistic Interpretability
David Bau on How—and Whether—Artificial Intelligence Thinks
David Bau on How Artificial Intelligence Works
Neural Mechanics Week 3: Evaluation and LLM-generated Data with David Bau
ROME: Locating and Editing Factual Associations in GPT with David Bau
Rewriting a Deep Generative Model (Preview)
Neural Mechanics Week 4: Representation Geometry with David Bau
View Detailed Profile
David Bau: Interpretability and model editing

David Bau: Interpretability and model editing

You can find more information including the the course syllabus and suggested readings at ...

Introduction to Mechanistic Interpretability with David Bau

Introduction to Mechanistic Interpretability with David Bau

CS 7180: Neural Mechanics Spring 2026 Course at Northeastern University Modern AI systems are powerful but opaque: even ...

David Bau – Resilience and Interpretability

David Bau – Resilience and Interpretability

David Bau

"In Defense of Curiosity" with David Bau (NeurIPS 2025 Mech Interp Workshop)

"In Defense of Curiosity" with David Bau (NeurIPS 2025 Mech Interp Workshop)

David Bau

Neural Mechanics Week 1: LLM Foundations and Logit Lens with David Bau

Neural Mechanics Week 1: LLM Foundations and Logit Lens with David Bau

David Bau

David Bau - Direct Model Editing and Mechanistic Interpretability

David Bau - Direct Model Editing and Mechanistic Interpretability

BlackboxNLP 2022 keynote by

David Bau on How—and Whether—Artificial Intelligence Thinks

David Bau on How—and Whether—Artificial Intelligence Thinks

David Bau

David Bau on How Artificial Intelligence Works

David Bau on How Artificial Intelligence Works

David Bau

Neural Mechanics Week 3: Evaluation and LLM-generated Data with David Bau

Neural Mechanics Week 3: Evaluation and LLM-generated Data with David Bau

David Bau

ROME: Locating and Editing Factual Associations in GPT with David Bau

ROME: Locating and Editing Factual Associations in GPT with David Bau

David Bau

Rewriting a Deep Generative Model (Preview)

Rewriting a Deep Generative Model (Preview)

You wouldn't normally fiddle with weights of a state-of-the-art deep network after weeks of training. But why not? In this ECCV ...

Neural Mechanics Week 4: Representation Geometry with David Bau

Neural Mechanics Week 4: Representation Geometry with David Bau

In the next Neural Mechanics class,

David Bau—Editing Facts in GPT, Interpretability

David Bau—Editing Facts in GPT, Interpretability

David Bau