AI ALIGNMENT FORUMTags
AF

Interpretability (ML & AI)

•

Applied to Announcing Apollo Research by Marius Hobbhahn 5h ago

•

Applied to Aligning an H-JEPA agent via training on the outputs of an LLM-based "exemplary actor" by Roman Leventov 10h ago

•

Applied to The king token by p.b. 2d ago

•

Applied to Why and When Interpretability Work is Dangerous by Nicholas Kross 3d ago

•

Applied to Solving the Mechanistic Interpretability challenges: EIS VII Challenge 2 by Stefan Heimersheim 5d ago

•

Applied to [Linkpost] Interpretability Dreams by DanielFilan 6d ago

•

Applied to 'Fundamental' vs 'applied' mechanistic interpretability research by Lee Sharkey 7d ago

•

Applied to Activation additions in a small residual network by Raymond Arnold 8d ago

•

Applied to Gender Vectors in ROME’s Latent Space by Xodarap 9d ago

•

Applied to A Mechanistic Interpretability Analysis of a GridWorld Agent-Simulator (Part 1 of N) by Joseph Isaac Bloom 14d ago

•

Applied to My current workflow to study the internal mechanisms of LLM by Yulu Pi 14d ago

•

Applied to Input Swap Graphs: Discovering the role of neural network components at scale by Alexandre Variengien 18d ago

•

Applied to AI interpretability could be harmful? by Roman Leventov 20d ago

•

Applied to New OpenAI Paper - Language models can explain neurons in language models by Raymond Arnold 20d ago

•

Applied to AGI-Automated Interpretability is Suicide by __RicG__ 20d ago

•

Applied to Have you heard about MIT's "liquid neural networks"? What do you think about them? by Ppau 21d ago

•

Applied to Solving the Mechanistic Interpretability challenges: EIS VII Challenge 1 by Stefan Heimersheim 21d ago