Sparse Crosscoders for diffing MoEs and Dense models
Mixture of Experts (MoE) achieve parameter-efficient scaling through sparse expert routing, yet their internal representations remain poorly understood compared to dense models. We present a systematic comparison of MoE and dense model internals using crosscoders, a variant of sparse autoencoders, that jointly models multiple activation spaces. We train 5-layer dense and MoEs (equal active parameters) on 1B tokens across code, scientific text, and english stories. Using BatchTopK crosscoders with explicitly designated shared features, we achieve $\sim 87\%$ fractional variance explained and uncover concrete differences in feature organization. The MoE learns significantly fewer unique features compared to the dense model. MoE-specific features also exhibit higher activation density than shared features, whereas dense-specific features show lower density. Our analysis reveals that MoEs develop more specialized, focused representations while dense models distribute information across broader, more general-purpose features.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Cross-Architecture Model Diffing with Crosscoders: Unsupervised Discovery of Differences Between LLMs
Model diffing, the process of comparing models' internal representations to identify their differences, is a promising approach for uncovering safety-critical behaviors in new models. However, its application has so far …
Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimes
Model diffing methods aim to identify how fine-tuning changes a model's internal representations. Crosscoders approach this by learning shared dictionaries of interpretable latent directions between base and fine-tuned m…
Robustly identifying concepts introduced during chat fine-tuning using crosscoders
Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviours of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpr…
Beyond the Leaderboard: Understanding Performance Disparities in Large Language Models via Model Diffing
As fine-tuning becomes the dominant paradigm for improving large language models (LLMs), understanding what changes during this process is increasingly important. Traditional benchmarking often fails to explain why one m…
Mobile V-MoEs: Scaling Down Vision Transformers via Sparse Mixture-of-Experts
Sparse Mixture-of-Experts models (MoEs) have recently gained popularity due to their ability to decouple model size from inference efficiency by only activating a small subset of the model parameters for any given input …
Mixture-of-Experts