AI ALIGNMENT FORUMTags
AF

Interpretability (ML & AI)

•

Applied to Effects of Non-Uniform Sparsity on Superposition in Toy Models by Shreyans Jain 6d ago

•

Applied to Antonym Heads Predict Semantic Opposites in Language Models by Jake Ward 7d ago

•

Applied to Analyzing how SAE features evolve across a forward pass by bensenberner 14d ago

•

Applied to SAEs are highly dataset dependent: a case study on the refusal direction by Connor Kissane 16d ago

•

Applied to Evolutionary prompt optimization for SAE feature visualization by neverix 18d ago

•

Applied to Testing "True" Language Understanding in LLMs: A Simple Proposal by MtryaSam 20d ago

•

Applied to Composition Circuits in Vision Transformers (Hypothesis) by phenomanon 20d ago

•

Applied to SAE Probing: What is it good for? Absolutely something! by Subhash Kantamneni 21d ago

•

Applied to Bridging the VLM and mech interp communities for multimodal interpretability by Sonia Joseph 25d ago

•

Applied to Open Source Replication of Anthropic’s Crosscoder paper for model-diffing by Connor Kissane 26d ago

•

Applied to Enabling New Applications with Today's Mechanistic Interpretability Toolkit by ananya_joshi 1mo ago

•

Applied to SAEs you can See: Applying Sparse Autoencoders to Clustering by Robert_AIZI 1mo ago

•

Applied to Monosemanticity & Quantization by Rahul Chand 1mo ago

•

Applied to A Rocket–Interpretability Analogy by plex 1mo ago

•

Applied to A short project on Mamba: grokking & interpretability by Alejandro Tlaie Boria 1mo ago

•

Applied to The Computational Complexity of Circuit Discovery for Inner Interpretability by Bogdan Ionut Cirstea 1mo ago

•

Applied to Circuits in Superposition: Compressing many small neural networks into one by Lucius Bushnaq 1mo ago

•

Applied to It's important to know when to stop: Mechanistic Exploration of Gemma 2 List Generation by Gerard Boxo 1mo ago