ARENA: AI interpretability

🌱 notes 🌱

During my second batch at RC, I joined a study group to cover the materials from Callum McDougall’s Alignment Research Engineer Accelerator aka ARENA program which is normally delivered by LISA: the London Initiative for Safe AI. ARENA is based on the MLAB AI alignment bootcamp by Redwood Research. Access to MLAB’s curriculum can be requested at the link.

Notes in the works!

Recommended reading

ImageNet Classification with Deep Convolutional Neural Networks

Generative Adversarial Nets

Attention is All You Need

A Mathematical Framework for Transformer Circuits

Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs — LessWrong

Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet

Additional resources

• See also my informal notes on: neural networks and AI

On the Measure of Intelligence - Chollet

CMU: Intro to machine learning

Neural networks: zero to hero (Karpathy)

Google: ML crash course: Linear regression

Neel Nanda 2024.07: An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forum