Image de couverture de livre

Does Transformer Interpretability Transfer to RNNs?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Paulo, Gonçalo, Marshall, Thomas, Belrose, Nora
Format:	Preprint
Publié:	2024
Sujets:	Machine Learning Artificial Intelligence Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Partially Rewriting a Transformer in Natural Language
par: Paulo, Gonçalo, et autres
Publié: (2025)

Automatically Interpreting Millions of Features in Large Language Models
par: Paulo, Gonçalo, et autres
Publié: (2024)

Eliciting Latent Knowledge from Quirky Language Models
par: Mallen, Alex, et autres
Publié: (2023)

Compositional Reasoning with Transformers, RNNs, and Chain of Thought
par: Yehudai, Gilad, et autres
Publié: (2025)

Refusal in LLMs is an Affine Function
par: Marshall, Thomas, et autres
Publié: (2024)

Transcoders Beat Sparse Autoencoders for Interpretability
par: Paulo, Gonçalo, et autres
Publié: (2025)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
par: Sun, Yu, et autres
Publié: (2024)

Evaluating SAE interpretability without explanations
par: Paulo, Gonçalo, et autres
Publié: (2025)

Sparse Autoencoders Trained on the Same Data Learn Different Features
par: Paulo, Gonçalo, et autres
Publié: (2025)

Examining Two Hop Reasoning Through Information Content Scaling
par: Johnston, David, et autres
Publié: (2025)

Enhancing Transformer RNNs with Multiple Temporal Perspectives
par: Dumitru, Razvan-Gabriel, et autres
Publié: (2024)

Atlas-Alignment: Making Interpretability Transferable Across Language Models
par: Puri, Bruno, et autres
Publié: (2025)

Discovering Interpretable Algorithms by Decompiling Transformers to RASP
par: Huang, Xinting, et autres
Publié: (2026)

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits
par: Ahmad, Areeb, et autres
Publié: (2025)

The Dual-Stream Transformer: Channelized Architecture for Interpretable Language Modeling
par: Kerce, J. Clayton, et autres
Publié: (2026)

Multi-Target Cross-Lingual Summarization: a novel task and a language-neutral approach
par: Pernes, Diogo, et autres
Publié: (2024)

Interpreting Key Mechanisms of Factual Recall in Transformer-Based Language Models
par: Lv, Ang, et autres
Publié: (2024)

Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions
par: Neo, Clement, et autres
Publié: (2024)

Cross-Architecture Transfer Learning for Linear-Cost Inference Transformers
par: Choi, Sehyun
Publié: (2024)

Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
par: Han, Sungmin, et autres
Publié: (2025)

Uncovering the Computational Roles of Nonlinearity in Sequence Modeling Using Almost-Linear RNNs
par: Brenner, Manuel, et autres
Publié: (2025)

Mechanistic Anomaly Detection for "Quirky" Language Models
par: Johnston, David O., et autres
Publié: (2025)

Sparse Autoencoder Features for Classifications and Transferability
par: Gallifant, Jack, et autres
Publié: (2025)

Why Don't Prompt-Based Fairness Metrics Correlate?
par: Zayed, Abdelrahman, et autres
Publié: (2024)

Should We Attend More or Less? Modulating Attention for Fairness
par: Zayed, Abdelrahman, et autres
Publié: (2023)

A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
par: Wu, Zhengxuan, et autres
Publié: (2024)

An evolutionary perspective on modes of learning in Transformers
par: Ku, Alexander Y., et autres
Publié: (2025)

Does Machine Unlearning Truly Remove Knowledge?
par: Chen, Haokun, et autres
Publié: (2025)

Interpreting the Effects of Quantization on LLMs
par: Singh, Manpreet, et autres
Publié: (2025)

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
par: Pepper, Keenan, et autres
Publié: (2026)

Does Biomedical Training Lead to Better Medical Performance?
par: Dada, Amin, et autres
Publié: (2024)

Does Refusal Training in LLMs Generalize to the Past Tense?
par: Andriushchenko, Maksym, et autres
Publié: (2024)

Instruction Fine-Tuning: Does Prompt Loss Matter?
par: Huerta-Enochian, Mathew, et autres
Publié: (2024)

Interpretable classification of wiki-review streams
par: Méndez, Silvia García, et autres
Publié: (2024)

Interpretable Question Answering with Knowledge Graphs
par: Aneja, Kartikeya, et autres
Publié: (2025)

MIB: A Mechanistic Interpretability Benchmark
par: Mueller, Aaron, et autres
Publié: (2025)

Does Differential Privacy Impact Bias in Pretrained NLP Models?
par: Islam, Md. Khairul, et autres
Publié: (2024)

How Does Response Length Affect Long-Form Factuality
par: Zhao, James Xu, et autres
Publié: (2025)

When Does Multimodality Lead to Better Time Series Forecasting?
par: Zhang, Xiyuan, et autres
Publié: (2025)

Does Training on Synthetic Data Make Models Less Robust?
par: Zhang, Lingze, et autres
Publié: (2025)