WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.
Attribution patching outperforms automated circuit discovery.arXiv preprint arXiv:2310.10348
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
Interaction locality is introduced as a task-geometry-aware measurement framework showing that high-level states in recursive models write locally while recursive updates build broader structures on maze, Sudoku, ARC-AGI, and 3D grounding tasks.
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
Circuit-based metrics from Vision Transformer internals provide better label-free proxies for generalization under distribution shift than existing methods like model confidence.
Pruning removes 'unsafe tickets' from LLMs via gradient-free attribution, reducing harmful outputs and jailbreak vulnerability with minimal utility loss.
Attribution-guided pruning with contrastive relevance identifies behavior-specific circuits in small LLMs and removes as little as 0.03-0.3% of components to reduce toxicity or repetition while preserving general performance.
citing papers explorer
-
WriteSAE: Sparse Autoencoders for Recurrent State
WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.
-
Interaction Locality in Hierarchical Recursive Reasoning
Interaction locality is introduced as a task-geometry-aware measurement framework showing that high-level states in recursive models write locally while recursive updates build broader structures on maze, Sudoku, ARC-AGI, and 3D grounding tasks.
-
Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
A latent mediation framework with sparse autoencoders enables non-additive token-level influence attribution in LLMs by learning orthogonal features and back-propagating attributions.
-
Instructions Shape Production of Language, not Processing
Instructions trigger a production-centered mechanism in language models, with task-specific information stable in input tokens but varying strongly in output tokens and correlating with behavior.
-
Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs
DACO curates a 15,000-concept dictionary from 400K image-caption pairs and uses it to initialize an SAE that enables granular, concept-specific steering of MLLM activations, raising safety scores on MM-SafetyBench and JailBreakV while preserving general capabilities.
-
Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings
Circuit-based metrics from Vision Transformer internals provide better label-free proxies for generalization under distribution shift than existing methods like model confidence.
-
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
Pruning removes 'unsafe tickets' from LLMs via gradient-free attribution, reducing harmful outputs and jailbreak vulnerability with minimal utility loss.
-
Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs
Attribution-guided pruning with contrastive relevance identifies behavior-specific circuits in small LLMs and removes as little as 0.03-0.3% of components to reduce toxicity or repetition while preserving general performance.