LESSWRONGTags
LW

Interpretability (ML & AI)

•

Applied to Adam Optimizer Causes Privileged Basis in Transformer Language Models by Diego Caples 2d ago

•

Applied to Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs by Daniel Lee 3d ago

•

Applied to Automating LLM Auditing with Developmental Interpretability by Raemon 4d ago

•

Applied to Redundant Attention Heads in Large Language Models For In Context Learning by skunnavakkam 7d ago

•

Applied to Can Large Language Models effectively identify cybersecurity risks? by emile delcourt 9d ago

•

Applied to Deception and Jailbreak Sequence: 2. Iterative Refinement Stages of Jailbreaks in LLM by Winnie Yang 9d ago

•

Applied to [Paper] Measuring Visual Sycophancy in Multimodal Models by Jaehyuk Lim 12d ago

•

Applied to AXRP Episode 35 - Peter Hase on LLM Beliefs and Easy-to-Hard Generalization by DanielFilan 15d ago

•

Applied to Understanding Hidden Computations in Chain-of-Thought Reasoning by rokosbasilisk 15d ago

•

Applied to Showing SAE Latents Are Not Atomic Using Meta-SAEs by Bart Bussmann 16d ago

•

Applied to Deception and Jailbreak Sequence: 1. Iterative Refinement Stages of Deception in LLMs by Winnie Yang 16d ago

•

Applied to Establishing a Connection (Ch. 5-8) by a littoral wizard 16d ago

•

Applied to Crafting Polysemantic Transformer Benchmarks with Known Circuits by Evan Anders 16d ago

•

Applied to Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs by Kola Ayonrinde 16d ago

•

Applied to Measuring Structure Development in Algorithmic Transformers by Raemon 17d ago

•

Applied to What's going on with Per-Component Weight Updates? by 4gate 18d ago

•

Applied to Finding Deception in Language Models by Esben Kran 19d ago

•

Applied to Biases in Biases, or Critique of the Critique by ThePathYouWillChoose 21d ago

•

Applied to Calendar feature geometry in GPT-2 layer 8 residual stream SAEs by Patrick Leask 23d ago