12 items with this tag.12/16/2024Creating Interpretable Latent Spaces with Gradient Routinginterpretabilitymats programAI12/5/2024Gradient Routing: Masking Gradients to Localize Computation in Neural Networksinterpretabilitymats programAI12/4/2024Deep Causal Transcoding: A Framework for Mechanistically Eliciting Latent Behaviors in Language Modelsactivation engineeringinterpretabilitymats programAI10/27/2024Can Transformers Act on Information Beyond an Effective Layer Horizon?understanding the worldinterpretabilityAI7/15/2024I Found >800 Orthogonal “Write Code” Steering Vectorsactivation engineeringinterpretabilitymats programAI4/30/2024Mechanistically Eliciting Latent Behaviors in Language Modelsunderstanding the worldactivation engineeringinterpretabilitymats programAI10/13/2023Paper: Understanding and Controlling a Maze-Solving Policy Networkactivation engineeringinterpretabilityshard theoryAI5/7/2023Residual Stream Norms Grow Exponentially over the Forward PassinterpretabilityAI4/20/2023Behavioural Statistics for a Maze-Solving Agentinterpretabilitymats programshard theoryAI3/31/2023Maze-Solving Agents: Add a Top-Right Vector, Make the Agent Go to the Top-Rightactivation engineeringinterpretabilityAI3/11/2023Understanding and Controlling a Maze-Solving Policy Networkactivation engineeringinterpretabilitymats programshard theoryAI3/1/2023Predictions for Shard Theory Mechanistic Interpretability Resultsinterpretabilitymats programshard theoryrationalityAI