NDIF Team

Opening AI's Black Box with NDIF LLM Crash Course and Workbench Demo

NDIF Team

Neural Mechanics Week 9 Training Dynamics, Patchscopes & Human Understanding with David Bau

NDIF Team

Neural Mechanics Week 8 Circuits with Nikhil Prakash

NDIF Team

Neural Mechanics Week 7 Attribution with Gabriele Sarti

NDIF Team

Neural Mechanics Week 6 Probing with David Bau

NDIF Team

Neural Mechanics Week 5 Causal Localization with David Bau

NDIF Team

Neural Mechanics Week 4 Representation Geometry with David Bau

NDIF Team

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

NDIF Team

Neural Mechanics Week 2 Concepts as Vectors and Steering with David Bau

NDIF Team

Auditing Language Models for Hidden Objectives with Sam Marks

NDIF Team

NDIF lightning talk at NeurIPS 2025 Mechanistic Interpretability Workshop with Adam Belfki

NDIF Team

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

NDIF Team

Equifinality There’s Often Multiple Explanations with Sheridan Feucht

NDIF Team

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

NDIF Team

Annus Mirabilis A Year of Explosive Progress in LLMs with Benjamin Feuer

NDIF Team

Introduction to Mechanistic Interpretability with David Bau

NDIF Team

Interpreting and Leveraging Diffusion Representations with Deepti Ghadiyaram

NDIF Team

Workbench Logit Lens Demo

NDIF Team

Interpreting SDXL Turbo Using Sparse Autoencoders with Chris Wendler

NDIF Team

Visual Contextual Effects and Feature Interactions in Vision Transformers with Xu Pan

NDIF Team

Sparse Autoencoders Progress & Limitations with Joshua Engels

NDIF Team

Understanding Inter-layer Communication in Transformer Language Models with Jack Merullo

NDIF Team

Attribute-to-Delete Machine Unlearning via Datamodel Matching with Roy Rinberg

NDIF Team

ROME Locating and Editing Factual Associations in GPT with David Bau

NDIF Team