Many distinct SAE features share identical explanations, with the average annotation resolving only 70% of feature identity in a large annotated dataset.
International Conference on Learning Representations (ICLR) , year =
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
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.
Cosine-scored SAEs with a learned direction-magnitude blend learn more concept-aligned features than standard inner-product SAEs at matched reconstruction quality.
SA-GSAE with Bi-Jump-ReLU enables one latent to encode both polarities of anticorrelated features, Pareto-dominating or matching full-width gated SAEs while reducing dead latents by up to 500x on some LLM hookpoints.
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
Tree SAE learns hierarchical feature structures by combining activation coverage with a new reconstruction condition, outperforming prior SAEs on hierarchical pair detection while matching state-of-the-art benchmark performance.
A new framework combines AI-derived concept embeddings with high-dimensional selective inference to enable statistically principled, interpretable discovery from unstructured data in empirical economics.
Mechanistic interpretability papers substitute validation metrics for causal identification without stating assumptions, and the authors propose a disclosure norm requiring explicit identification strategies.
Sparse autoencoders show OOD prompts increase fallacious concept activation in transformers, offering a mechanistic measure of shift and a path to robust fine-tuning.
citing papers explorer
-
Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features
Many distinct SAE features share identical explanations, with the average annotation resolving only 70% of feature identity in a large annotated dataset.
-
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.
-
Size Doesn't Matter: Cosine-Scored Sparse Autoencoders
Cosine-scored SAEs with a learned direction-magnitude blend learn more concept-aligned features than standard inner-product SAEs at matched reconstruction quality.
-
Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations
SA-GSAE with Bi-Jump-ReLU enables one latent to encode both polarities of anticorrelated features, Pareto-dominating or matching full-width gated SAEs while reducing dead latents by up to 500x on some LLM hookpoints.
-
Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning
SAEParate disentangles sparse representations in diffusion models via contrastive clustering and nonlinear encoding to enable more precise concept unlearning with reduced side effects.
-
Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders
Tree SAE learns hierarchical feature structures by combining activation coverage with a new reconstruction condition, outperforming prior SAEs on hierarchical pair detection while matching state-of-the-art benchmark performance.
-
Position: Mechanistic Interpretability Must Disclose Identification Assumptions for Causal Claims
Mechanistic interpretability papers substitute validation metrics for causal identification without stating assumptions, and the authors propose a disclosure norm requiring explicit identification strategies.
-
At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization
Sparse autoencoders show OOD prompts increase fallacious concept activation in transformers, offering a mechanistic measure of shift and a path to robust fine-tuning.