Transformers

Applied to Analyzing how SAE features evolve across a forward pass by bensenberner 2mo ago

Applied to Transformers Explained (Again) by Rohan Subramani 2mo ago

Applied to Characterizing stable regions in the residual stream of LLMs by Jett Janiak 3mo ago

Applied to If I ask an LLM to think step by step, how big are the steps? by Ryan Blough 4mo ago

Applied to Adam Optimizer Causes Privileged Basis in Transformer LM Residual Stream by Diego Caples 4mo ago

Applied to Visualizing small Attention-only Transformers by Léo Dana 4mo ago

Applied to How Big a Deal are MatMul-Free Transformers? by JustisMills 6mo ago

Applied to Week One of Studying Transformers Architecture by JustisMills 6mo ago

Applied to Logit Prisms: Decomposing Transformer Outputs for Mechanistic Interpretability by ntt123 7mo ago

Applied to Exploring Llama-3-8B MLP Neurons by ntt123 7mo ago

Applied to Finding Backward Chaining Circuits in Transformers Trained on Tree Search by abhayesian 7mo ago

Applied to If language is for communication, what does that imply about LLMs? by Bill Benzon 8mo ago

Applied to An interesting mathematical model of how LLMs work by Bill Benzon 8mo ago

Applied to Transformers Represent Belief State Geometry in their Residual Stream by Adam Shai 9mo ago

Applied to Barcoding LLM Training Data Subsets. Anyone trying this for interpretability? by right..enough? 9mo ago

Applied to Understanding mesa-optimization using toy models by tilmanr 9mo ago

Applied to Decompiling Tracr Transformers - An interpretability experiment by Hannes Thurnherr 9mo ago

Applied to Modern Transformers are AGI, and Human-Level by jacobjacob 9mo ago

Applied to Deconfusing In-Context Learning by Arjun Panickssery 10mo ago