MATS Program

Applied to End-to-end hacking with language models by Timothée Chauvin 21d ago

Applied to Ophiology (or, how the Mamba architecture works) by Danielle Ensign 23d ago

Applied to My MATS Summer 2023 experience by James Chua 1mo ago

Applied to Understanding SAE Features with the Logit Lens by Joseph Isaac Bloom 2mo ago

Applied to MATS AI Safety Strategy Curriculum by Ryan Kidd 2mo ago

Applied to We Inspected Every Head In GPT-2 Small using SAEs So You Don’t Have To by robertzk 2mo ago

Applied to Implementing activation steering by Annah 3mo ago

Applied to Attention SAEs Scale to GPT-2 Small by robertzk 3mo ago

Applied to How important is AI hacking as LLMs advance? by artkpv 3mo ago

Applied to Uncertainty in all its flavours by Cleo Nardo 3mo ago

Applied to Sparse Autoencoders Work on Attention Layer Outputs by robertzk 3mo ago

Applied to Case Studies in Reverse-Engineering Sparse Autoencoder Features by Using MLP Linearization by Jacob Dunefsky 4mo ago

Applied to Steering Llama-2 with contrastive activation additions by Alex Turner 4mo ago

Applied to Interview: Applications w/ Alice Rigg by jacobhaimes 4mo ago

Applied to MATS Summer 2023 Retrospective by Ryan Kidd 5mo ago

Applied to Classifying representations of sparse autoencoders (SAEs) by Annah 5mo ago

Applied to Game Theory without Argmax [Part 2] by Cleo Nardo 5mo ago

Applied to Game Theory without Argmax [Part 1] by Cleo Nardo 5mo ago

Applied to Polysemantic Attention Head in a 4-Layer Transformer by Jett Janiak 6mo ago