8 papers · 1 filter
Investigating Representation Universality: Case Study on Genealogical Representations
David D. Baek, Yuxiao Li, Max Tegmark
Motivated by interpretability and reliability, we investigate whether large language models (LLMs) deploy universal geometric structures to encode discrete, graph-structured knowle…
Dense SAE Latents Are Features, Not Bugs
Xiaoqing Sun, Alessandro Stolfo, Joshua Engels +4
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…
Efficient Dictionary Learning with Switch Sparse Autoencoders
Anish Mudide, Joshua Engels, Eric J. Michaud +2
Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features…
Low-Rank Adapting Models for Sparse Autoencoders
Matthew Chen, Joshua Engels, Max Tegmark
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…
Towards Understanding Distilled Reasoning Models: A Representational Approach
David D. Baek, Max Tegmark
In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-s…
Decomposing The Dark Matter of Sparse Autoencoders
Joshua Engels, Logan Riggs, Max Tegmark
Sparse autoencoders (SAEs) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely e…