AI ALIGNMENT FORUMTags
AF

Interpretability (ML & AI)

•

Applied to Visualizing neural network planning by Nevan Wichers 6h ago

•

Applied to Mechanistic Interpretability Workshop Happening at ICML 2024! by Neel Nanda 6d ago

•

Applied to KAN: Kolmogorov-Arnold Networks by Gunnar Zarncke 8d ago

•

Applied to Transcoders enable fine-grained interpretable circuit analysis for language models by Jacob Dunefsky 9d ago

•

Applied to Towards Multimodal Interpretability: Learning Sparse Interpretable Features in Vision Transformers by Vanessa Kosoy 9d ago

•

Applied to Refusal in LLMs is mediated by a single direction by Neel Nanda 11d ago

•

Applied to Why I stopped being into basin broadness by Gunnar Zarncke 13d ago

•

Applied to Superposition is not "just" neuron polysemanticity by Lawrence Chan 13d ago

•

Applied to Improving Dictionary Learning with Gated Sparse Autoencoders by Neel Nanda 14d ago

•

Applied to ProLU: A Nonlinearity for Sparse Autoencoders by Noa Nabeshima 16d ago

•

Applied to How to use and interpret activation patching by Stefan Heimersheim 18d ago

•

Applied to Past Tense Features by Can 19d ago

•

Applied to [Full Post] Progress Update #1 from the GDM Mech Interp Team by Neel Nanda 20d ago

•

Applied to [Summary] Progress Update #1 from the GDM Mech Interp Team by Neel Nanda 20d ago

•

Applied to Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight by Raymond Arnold 21d ago

•

Applied to Transformers Represent Belief State Geometry in their Residual Stream by Adam Shai 23d ago

•

Applied to Experiments with an alternative method to promote sparsity in sparse autoencoders by Eoin Farrell 23d ago

•

Applied to Barcoding LLM Training Data Subsets. Anyone trying this for interpretability? by right..enough? 1mo ago

•

Applied to Scaling Laws and Superposition by Pavan Katta 1mo ago