Imagen de Portada

Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	O'Neill, Charles, Jayasekara, Mudith, Kirkby, Max
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
por: O'Neill, Charles, et al.
Publicado: (2025)

Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
por: O'Neill, Charles, et al.
Publicado: (2024)

Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
por: O'Neill, Charles, et al.
Publicado: (2024)

Disentangling Dense Embeddings with Sparse Autoencoders
por: O'Neill, Charles, et al.
Publicado: (2024)

Self-Attention as a Parametric Endofunctor: A Categorical Framework for Transformer Architectures
por: O'Neill, Charles
Publicado: (2025)

Mechanistic Interpretability with Sparse Autoencoder Neural Operators
por: Tolooshams, Bahareh, et al.
Publicado: (2025)

Group Equivariance Meets Mechanistic Interpretability: Equivariant Sparse Autoencoders
por: Erdogan, Ege, et al.
Publicado: (2025)

Mechanistic Interpretability of Code Correctness in LLMs via Sparse Autoencoders
por: Tahimic, Kriz, et al.
Publicado: (2025)

Type 2 Tobit Sample Selection Models with Bayesian Additive Regression Trees
por: O'Neill, Eoghan
Publicado: (2025)

Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders
por: Lehn-Schiøler, William, et al.
Publicado: (2026)

Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
por: Miller, Jack, et al.
Publicado: (2023)

DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders
por: Wang, Xu, et al.
Publicado: (2026)

Transcoders Beat Sparse Autoencoders for Interpretability
por: Paulo, Gonçalo, et al.
Publicado: (2025)

Decomposing The Dark Matter of Sparse Autoencoders
por: Engels, Joshua, et al.
Publicado: (2024)

Interpretable Reward Model via Sparse Autoencoder
por: Zhang, Shuyi, et al.
Publicado: (2025)

Interpreting Attention Layer Outputs with Sparse Autoencoders
por: Kissane, Connor, et al.
Publicado: (2024)

Low-Rank Adapting Models for Sparse Autoencoders
por: Chen, Matthew, et al.
Publicado: (2025)

Route Sparse Autoencoder to Interpret Large Language Models
por: Shi, Wei, et al.
Publicado: (2025)

Step-Level Sparse Autoencoder for Reasoning Process Interpretation
por: Yang, Xuan, et al.
Publicado: (2026)

Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
por: Makelov, Aleksandar, et al.
Publicado: (2024)

Binary Autoencoder for Mechanistic Interpretability of Large Language Models
por: Cho, Hakaze, et al.
Publicado: (2025)

A Multi-Level Causal Intervention Framework for Mechanistic Interpretability in Variational Autoencoders
por: Roy, Dip, et al.
Publicado: (2025)

Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders
por: Zheng, Carolina, et al.
Publicado: (2025)

Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders
por: Ye, Mengyu, et al.
Publicado: (2025)

Enhancing Neural Network Interpretability with Feature-Aligned Sparse Autoencoders
por: Marks, Luke, et al.
Publicado: (2024)

Sketching the Heat Kernel: Using Gaussian Processes to Embed Data
por: Gilbert, Anna C., et al.
Publicado: (2024)

Interpretable Company Similarity with Sparse Autoencoders
por: Molinari, Marco, et al.
Publicado: (2024)

Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders
por: Kurochkin, Vadim, et al.
Publicado: (2025)

Efficient Dictionary Learning with Switch Sparse Autoencoders
por: Mudide, Anish, et al.
Publicado: (2024)

From superposition to sparse codes: interpretable representations in neural networks
por: Klindt, David, et al.
Publicado: (2025)

Are Sparse Autoencoders Useful? A Case Study in Sparse Probing
por: Kantamneni, Subhash, et al.
Publicado: (2025)

Measuring Sharpness in Grokking
por: Miller, Jack, et al.
Publicado: (2024)

Interpreting CLIP with Hierarchical Sparse Autoencoders
por: Zaigrajew, Vladimir, et al.
Publicado: (2025)

Interpreting and Steering Protein Language Models through Sparse Autoencoders
por: Garcia, Edith Natalia Villegas, et al.
Publicado: (2025)

Modelling the Doughnut of social and planetary boundaries with frugal machine learning
por: Vrizzi, Stefano, et al.
Publicado: (2025)

Interpreting CFD Surrogates through Sparse Autoencoders
por: Hu, Yeping, et al.
Publicado: (2025)

Interpretable and Steerable Concept Bottleneck Sparse Autoencoders
por: Kulkarni, Akshay, et al.
Publicado: (2025)

XNNTab -- Interpretable Neural Networks for Tabular Data using Sparse Autoencoders
por: Elhadri, Khawla, et al.
Publicado: (2025)

Towards Interpretable Protein Structure Prediction with Sparse Autoencoders
por: Parsan, Nithin, et al.
Publicado: (2025)

AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features
por: Zhu, Xudong, et al.
Publicado: (2025)