Imagen de Portada

Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Karvonen, Adam, Rager, Can, Marks, Samuel, Nanda, Neel
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
por: Karvonen, Adam, et al.
Publicado: (2025)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
por: Casademunt, Helena, et al.
Publicado: (2025)

Robustly Improving LLM Fairness in Realistic Settings via Interpretability
por: Karvonen, Adam, et al.
Publicado: (2025)

Learning Multi-Level Features with Matryoshka Sparse Autoencoders
por: Bussmann, Bart, et al.
Publicado: (2025)

Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
por: Marks, Samuel, et al.
Publicado: (2024)

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
por: Karvonen, Adam, et al.
Publicado: (2024)

Emergent World Models and Latent Variable Estimation in Chess-Playing Language Models
por: Karvonen, Adam
Publicado: (2024)

Kernelized Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
por: Casademunt, Helena, et al.
Publicado: (2026)

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
por: Li, Aaron J., et al.
Publicado: (2025)

AlignSAE: Concept-Aligned Sparse Autoencoders
por: Yang, Minglai, et al.
Publicado: (2025)

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

Linear Adversarial Concept Erasure
por: Ravfogel, Shauli, et al.
Publicado: (2022)

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2
por: Lieberum, Tom, et al.
Publicado: (2024)

Explorations of Self-Repair in Language Models
por: Rushing, Cody, et al.
Publicado: (2024)

Revisiting End-To-End Sparse Autoencoder Training: A Short Finetune Is All You Need
por: Karvonen, Adam
Publicado: (2025)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
por: Zhang, Fred, et al.
Publicado: (2023)

Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts
por: Yan, Xinyuan, et al.
Publicado: (2025)

Transcoders Find Interpretable LLM Feature Circuits
por: Dunefsky, Jacob, et al.
Publicado: (2024)

Summing Up the Facts: Additive Mechanisms Behind Factual Recall in LLMs
por: Chughtai, Bilal, et al.
Publicado: (2024)

TaCo: Targeted Concept Erasure Prevents Non-Linear Classifiers From Detecting Protected Attributes
por: Jourdan, Fanny, et al.
Publicado: (2023)

Nonlinear Concept Erasure: a Density Matching Approach
por: Saillenfest, Antoine, et al.
Publicado: (2025)

Use Sparse Autoencoders to Discover Unknown Concepts, Not to Act on Known Concepts
por: Peng, Kenny, et al.
Publicado: (2025)

BatchTopK Sparse Autoencoders
por: Bussmann, Bart, et al.
Publicado: (2024)

Discovering Forbidden Topics in Language Models
por: Rager, Can, et al.
Publicado: (2025)

AtP*: An efficient and scalable method for localizing LLM behaviour to components
por: Kramár, János, et al.
Publicado: (2024)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
por: Chalnev, Sviatoslav, et al.
Publicado: (2024)

Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
por: Karvonen, Adam, et al.
Publicado: (2025)

Sparse Shift Autoencoders for Identifying Concepts from Large Language Model Activations
por: Joshi, Shruti, et al.
Publicado: (2025)

Automatically Finding Rule-Based Neurons in OthelloGPT
por: Singh, Aditya, et al.
Publicado: (2025)

Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models
por: Muhamed, Aashiq, et al.
Publicado: (2024)

Do Sparse Autoencoders Capture Concept Manifolds?
por: Bhalla, Usha, et al.
Publicado: (2026)

Steering Evaluation-Aware Language Models to Act Like They Are Deployed
por: Hua, Tim Tian, et al.
Publicado: (2025)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
por: Ferrando, Javier, et al.
Publicado: (2024)

Simple Mechanistic Explanations for Out-Of-Context Reasoning
por: Wang, Atticus, et al.
Publicado: (2025)

Training Superior Sparse Autoencoders for Instruct Models
por: Li, Jiaming, et al.
Publicado: (2025)

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words
por: Minegishi, Gouki, et al.
Publicado: (2025)

Erasing with Precision: Evaluating Specific Concept Erasure from Text-to-Image Generative Models
por: Fuchi, Masane, et al.
Publicado: (2025)

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

Thought Branches: Interpreting LLM Reasoning Requires Resampling
por: Macar, Uzay, et al.
Publicado: (2025)