conftrace_

sparse autoencoder

112 papers

Explore in graph

Co-occurring keywords

large language model (13587) mechanistic interpretability (133) feature extraction (1580) language model (4599) representation learning (6206) model interpretability (519) steering vector (33) feature steering (6) feature decomposition (51) interpretable feature (23)

Papers

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering NAACL 2025
Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages NAACL 2025
Analyzing (In)Abilities of SAEs via Formal Languages NAACL 2025
Disentangling language change: sparse autoencoders quantify the semantic evolution of indigeneity in French NAACL 2025
Interpret and Control Dense Retrieval with Sparse Latent Features NAACL 2025
Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models NAACL 2025
Interpretable Company Similarity with Sparse Autoencoders ACL 2025
Understanding the Repeat Curse in Large Language Models from a Feature Perspective ACL 2025
Feature-Level Insights into Artificial Text Detection with Sparse Autoencoders ACL 2025
Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms ACL 2025
Sparse Latents Steer Retrieval-Augmented Generation ACL 2025
Beyond Input Activations: Identifying Influential Latents by Gradient Sparse Autoencoders EMNLP 2025
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models EMNLP 2025
Route Sparse Autoencoder to Interpret Large Language Models EMNLP 2025
Sparse Autoencoder Features for Classifications and Transferability EMNLP 2025
Improving LLM Reasoning through Interpretable Role-Playing Steering EMNLP 2025
A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models EMNLP 2025
On the Versatility of Sparse Autoencoders for In-Context Learning EMNLP 2025
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs EMNLP 2025
CE-Bench: Towards a Reliable Contrastive Evaluation Benchmark of Interpretability of Sparse Autoencoders EMNLP 2025
PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders EMNLP 2025
Extended Abstract for “Linguistic Universals”: Emergent Shared Features in Independent Monolingual Language Models via Sparse Autoencoders EMNLP 2025
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning NIPS 2024
Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 EMNLP 2024
Accelerating Sparse Autoencoder Training via Layer-Wise Transfer Learning in Large Language Models EMNLP 2024