Related papers: Towards Interpretable Protein Structure Prediction…

Recent advancements in machine learning (ML) are transforming the field of structural biology. For example, AlphaFold, a groundbreaking neural network for protein structure prediction, has been widely adopted by researchers. The…

Large language models (LLMs) excel at handling human queries, but they can occasionally generate flawed or unexpected responses. Understanding their internal states is crucial for understanding their successes, diagnosing their failures,…

Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this joint space, and how do the models encode meaning and…

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Sparse autoencoders (SAEs) are used to decompose neural network activations into human-interpretable features. Typically, features learned by a single SAE are used for downstream applications. However, it has recently been shown that SAEs…

The mechanisms behind multilingual capabilities in Large Language Models (LLMs) have been examined using neuron-based or internal-activation-based methods. However, these methods often face challenges such as superposition and layer-wise…

Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that…

Fine-tuning Pre-trained protein language models (PLMs) has emerged as a prominent strategy for enhancing downstream prediction tasks, often outperforming traditional supervised learning approaches. As a widely applied powerful technique in…

While sparse autoencoders (SAEs) have generated significant excitement, a series of negative results have added to skepticism about their usefulness. Here, we establish a conceptual distinction that reconciles competing narratives…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for interpreting the features learned by large language models (LLMs). By reconstructing features with sparsely activated networks, SAEs aim to recover complex superposed…

Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization…

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Speech holds promise as a cost-effective and non-invasive biomarker for neurological conditions such as Parkinson's disease (PD). While deep learning systems trained on raw audio can find subtle signals not available from hand-crafted…

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Recovering meaningful concepts from language model activations is a central aim of interpretability. While existing feature extraction methods aim to identify concepts that are independent directions, it is unclear if this assumption can…

Protein structure prediction often hinges on multiple sequence alignments (MSAs), which underperform on low-homology and orphan proteins. We introduce PLAME, a lightweight MSA design framework that leverages evolutionary embeddings from…

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques such as \textit{sparse…

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture non-semantic…

Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…

The ImageNet hierarchy provides a structured taxonomy of object categories, offering a valuable lens through which to analyze the representations learned by deep vision models. In this work, we conduct a comprehensive analysis of how vision…