English
Related papers

Related papers: Improving Neuron-level Interpretability with White…

200 papers

Fine-tuning pre-trained transformers is a powerful technique for enhancing the performance of base models on specific tasks. From early applications in models like BERT to fine-tuning Large Language Models (LLMs), this approach has been…

Computation and Language · Computer Science 2025-02-25 Suneel Nadipalli

Recurrent neural networks (RNNs) are powerful and effective for processing sequential data. However, RNNs are usually considered "black box" models whose internal structure and learned parameters are not interpretable. In this paper, we…

Machine Learning · Statistics 2016-11-23 Scott Wisdom , Thomas Powers , James Pitton , Les Atlas

Sparse autoencoders (SAEs) extract human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation. We develop a model that plans ahead when it computes alignments between the…

Computation and Language · Computer Science 2017-06-26 Caglar Gulcehre , Francis Dutil , Adam Trischler , Yoshua Bengio

Sparse autoencoders (SAEs) have emerged as a promising approach for learning interpretable features from neural network activations. However, the optimization landscape for SAE training can be challenging due to correlations in the input…

Machine Learning · Computer Science 2025-11-19 Ashwin Saraswatula , David Klindt

Transformer-like models for vision tasks have recently proven effective for a wide range of downstream applications such as segmentation and detection. Previous works have shown that segmentation properties emerge in vision transformers…

Computer Vision and Pattern Recognition · Computer Science 2023-09-01 Yaodong Yu , Tianzhe Chu , Shengbang Tong , Ziyang Wu , Druv Pai , Sam Buchanan , Yi Ma

Latent reasoning compresses the chain-of-thought (CoT) into continuous hidden states, yet existing methods rely on dense latent transitions that remain difficult to interpret and control. Meanwhile, sparse representation models uncover…

Artificial Intelligence · Computer Science 2026-02-03 Yadong Wang , Haodong Chen , Yu Tian , Chuanxing Geng , Dong Liang , Xiang Chen

We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard…

Computation and Language · Computer Science 2019-10-31 Mike Lewis , Yinhan Liu , Naman Goyal , Marjan Ghazvininejad , Abdelrahman Mohamed , Omer Levy , Ves Stoyanov , Luke Zettlemoyer

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Machine Learning · Computer Science 2025-08-07 Gonçalo Paulo , Alex Mallen , Caden Juang , Nora Belrose

Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structure or computation information of the neural architectures.…

Machine Learning · Computer Science 2021-06-15 Shen Yan , Kaiqiang Song , Fei Liu , Mi Zhang

We present a methodology that explores how sentence structure is reflected in neural representations of machine translation systems. We demonstrate our model-agnostic approach with the Transformer English-German translation model. We…

Computation and Language · Computer Science 2022-11-04 Gal Patel , Leshem Choshen , Omri Abend

In Natural Language (NL) applications, there is often a mismatch between what the NL interface is capable of interpreting and what a lay user knows how to express. This work describes a novel natural language interface that reduces this…

Computation and Language · Computer Science 2020-12-14 Clifton McFate , Aditya Kalyanpur , Dave Ferrucci , Andrea Bradshaw , Ariel Diertani , David Melville , Lori Moon

Deep learning has excelled in medical image classification, but its clinical application is limited by poor interpretability. Capsule networks, known for encoding hierarchical relationships and spatial features, show potential in addressing…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Xinyu Geng , Jiaming Wang , Jun Xu

Transformer-based pre-trained language models have significantly improved the performance of various natural language processing (NLP) tasks in the recent years. While effective and prevalent, these models are usually prohibitively large…

Computation and Language · Computer Science 2022-01-19 Dongkuan Xu , Ian E. H. Yen , Jinxi Zhao , Zhibin Xiao

Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on scalar metrics, or require nontrivial integration effort,…

Computation and Language · Computer Science 2025-07-08 Nura Aljaafari , Danilo S. Carvalho , André Freitas

Autoencoders have been successful in learning meaningful representations from image datasets. However, their performance on text datasets has not been widely studied. Traditional autoencoders tend to learn possibly trivial representations…

Machine Learning · Statistics 2017-06-06 Yu Chen , Mohammed J. Zaki

This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, namely computational…

Computation and Language · Computer Science 2024-05-22 Charles O'Neill , Thang Bui

In the context of inverse problems $\bf y = Ax$, sparse recovery offers a powerful paradigm shift by enabling the stable solution of ill-posed or underdetermined systems through the exploitation of structure, particularly sparsity. Sparse…

Image and Video Processing · Electrical Eng. & Systems 2025-06-03 Di An , Dylan Poppert , Jiayue Li , Mark Foster , Trac D. Tran

Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is due to the filter-class entanglement -- an intricate…

Computer Vision and Pattern Recognition · Computer Science 2021-07-02 Haoyu Liang , Zhihao Ouyang , Yuyuan Zeng , Hang Su , Zihao He , Shu-Tao Xia , Jun Zhu , Bo Zhang

The field of natural language processing has reached breakthroughs with the advent of transformers. They have remained state-of-the-art since then, and there also has been much research in analyzing, interpreting, and evaluating the…

Computation and Language · Computer Science 2023-12-12 Soniya Vijayakumar