Related papers: Feature Hedging: Correlated Features Break Narrow …
Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising…
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…
Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…
Previous studies primarily utilize MLP neurons as units of analysis for understanding the mechanisms of factual knowledge in Language Models (LMs); however, neurons suffer from polysemanticity, leading to limited knowledge expression and…
Disentangling model activations into meaningful features is a central problem in interpretability. However, the absence of ground-truth for these features in realistic scenarios makes validating recent approaches, such as sparse dictionary…
Large Language Models (LLMs) have transformed natural language processing, yet their internal mechanisms remain largely opaque. Recently, mechanistic interpretability has attracted significant attention from the research community as a…
Understanding how features evolve across layers in deep neural networks is a fundamental challenge in mechanistic interpretability, particularly due to polysemanticity and feature superposition. While Sparse Autoencoders (SAEs) have been…
Sparse autoencoders (SAEs) have been widely used for interpretability of neural networks, but their learned features often vary across seeds and hyperparameter settings. We introduce Ordered Sparse Autoencoders (OSAE), which extend…
Sparse autoencoders (SAEs) are now standard tools for decomposing language model activations into interpretable features, and automated interpretability pipelines routinely assign each feature a short natural-language explanation. Existing…
Sparse autoencoders (SAEs) have been applied to large language models and protein language models, but not systematically to electronic health record (EHR) foundation models. We train TopK SAEs on FlatASCEND, a 14.5-million-parameter…
Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…
Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that are both sparse and semantically meaningful. However, many…
We investigate whether sparse autoencoders (SAEs) can be used to remove knowledge from language models. We use the biology subset of the Weapons of Mass Destruction Proxy dataset and test on the gemma-2b-it and gemma-2-2b-it language…
One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…
Sparse autoencoders (SAEs) decompose language model representations into a sparse set of linear latent vectors. Recent works have improved SAEs using language model gradients, but these techniques require many expensive backward passes…
Sparse Autoencoders (SAEs) are a powerful dictionary learning technique for decomposing neural network activations, translating the hidden state into human ideas with high semantic value despite no external intervention or guidance.…
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…
The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…
Sparse Autoencoders (SAEs) have emerged as a useful tool for interpreting the internal representations of neural networks. However, naively optimising SAEs for reconstruction loss and sparsity results in a preference for SAEs that are…
Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…