Related papers: SAEmnesia: Erasing Concepts in Diffusion Models wi…

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

In this paper, we propose a new unsupervised feature learning framework, namely Deep Sparse Coding (DeepSC), that extends sparse coding to a multi-layer architecture for visual object recognition tasks. The main innovation of the framework…

Sparse Autoencoders (SAEs) are powerful tools for interpreting neural representations, yet their use in audio remains underexplored. We train SAEs across all encoder layers of Whisper and HuBERT, provide an extensive evaluation of their…

As AI models achieve remarkable capabilities across diverse domains, understanding what representations they learn and how they encode concepts has become increasingly important for both scientific progress and trustworthy deployment.…

The prevalent use of commercial and open-source diffusion models (DMs) for text-to-image generation prompts risk mitigation to prevent undesired behaviors. Existing concept erasing methods in academia are all based on full parameter or…

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address…

The Universality Hypothesis in large language models (LLMs) claims that different models converge towards similar concept representations in their latent spaces. Providing evidence for this hypothesis would enable researchers to exploit…

Large-scale pre-trained vision-language models like CLIP demonstrate remarkable zero-shot performance across diverse tasks. However, fine-tuning these models to improve downstream performance often degrades robustness against distribution…

Concept erasure, which fine-tunes diffusion models to remove undesired or harmful visual concepts, has become a mainstream approach to mitigating unsafe or illegal image generation in text-to-image models.However, existing removal methods…

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation. Our philosophy is to deconstruct a DDM, gradually transforming it into a classical…

Image Generation models are a trending topic nowadays, with many people utilizing Artificial Intelligence models in order to generate images. There are many such models which, given a prompt of a text, will generate an image which depicts…

Sparse autoencoders (SAEs) provide a powerful mechanism for decomposing the dense representations produced by Large Language Models (LLMs) into interpretable latent features. We posit that SAEs constitute a natural foundation for Learned…

Sparse Autoencoders (SAEs) have shown promise in improving the interpretability of neural network activations, but can learn features that are not features of the input, limiting their effectiveness. We propose \textsc{Mutual Feature…

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…

Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…

Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to unlearn. Hence, we introduce a family of…