AI ALIGNMENT FORUMTags
AF

Interpretability (ML & AI)

•

Applied to Refusal mechanisms: initial experiments with Llama-2-7b-chat by Nina Rimsky 2h ago

•

Applied to Language Model Memorization, Copyright Law, and Conditional Pretraining Alignment by Roger Dearnaley 2d ago

•

Applied to Deep Forgetting & Unlearning for Safely-Scoped LLMs by Stephen Casper 3d ago

•

Applied to Mechanistic interpretability through clustering by Alistair Fraser 4d ago

•

Applied to Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study by Karolis Ramanauskas 4d ago

•

Applied to Why using activation for interpreting GPT-2? by sprout_ust 6d ago

•

Applied to How useful is mechanistic interpretability? by Ryan Greenblatt 8d ago

•

Applied to Intro to Superposition & Sparse Autoencoders (Colab exercises) by CallumMcDougall 9d ago

•

Applied to A day in the life of a mechanistic interpretability researcher by Bill Benzon 10d ago

•

Applied to AISC project: TinyEvals by Jett Janiak 16d ago

•

Applied to A framing for interpretability by Nina Rimsky 24d ago

•

Applied to Incidental polysemanticity by Victor Lecomte 25d ago

•

Applied to Is Interpretability All We Need? by Roger Dearnaley 25d ago

•

Applied to Eliciting Latent Knowledge in Comprehensive AI Services Models by acabodi 25d ago

•

Applied to AISC Project: Modelling Trajectories of Language Models by Nicky Pochinkov 25d ago

niplav v1.4.0Nov 10th 2023 (+40)

Explainable Artificial Intelligence on Wikipedia
Transformer Circuits
Interpretable Machine Learning, textbook