LESSWRONGTags
LW

Sparse Autoencoders (SAEs)

•

Applied to Towards Multimodal Interpretability: Learning Sparse Interpretable Features in Vision Transformers by Joseph Bloom 17d ago

•

Applied to Transcoders enable fine-grained interpretable circuit analysis for language models by Jacob Dunefsky 17d ago

•

Applied to Improving Dictionary Learning with Gated Sparse Autoencoders by Neel Nanda 22d ago

•

Applied to ProLU: A Nonlinearity for Sparse Autoencoders by Noa Nabeshima 24d ago

•

Applied to Discriminating Behaviorally Identical Classifiers: a model problem for applying interpretability to scalable oversight by Neel Nanda 26d ago

•

Applied to Past Tense Features by Can 1mo ago

•

Applied to [Summary] Progress Update #1 from the GDM Mech Interp Team by Joseph Bloom 1mo ago

•

Applied to [Full Post] Progress Update #1 from the GDM Mech Interp Team by Joseph Bloom 1mo ago

•

Applied to Experiments with an alternative method to promote sparsity in sparse autoencoders by Eoin Farrell 1mo ago

•

Applied to Normalizing Sparse Autoencoders by Fengyuan Hu 1mo ago

•

Applied to Improving SAE's by Sqrt()-ing L1 & Removing Lowest Activating Features by Joseph Bloom 1mo ago

•

Applied to SAE-VIS: Announcement Post by Joseph Bloom 1mo ago

•

Applied to SAE reconstruction errors are (empirically) pathological by Joseph Bloom 1mo ago

•

Applied to My best guess at the important tricks for training 1L SAEs by Joseph Bloom 1mo ago

•

Applied to Addressing Feature Suppression in SAEs by Joseph Bloom 1mo ago

•

Applied to Transformer Debugger by Joseph Bloom 1mo ago

•

Applied to Explainer - AutoInterpretation Finds Sparse Coding Beats Alternatives by Joseph Bloom 1mo ago

•

Applied to Sparse Coding, for Mechanistic Interpretability and Activation Engineering by Joseph Bloom 1mo ago