Train on prefill, monitor at decode: Using sparse autoencoders for topic monitoring
中文摘要
TopicScope利用稀疏自动编码器在模型生成过程中实时监测并标注每个token的主题,实现动态且细粒度的内容分类。
English Summary
TopicScope uses sparse autoencoders to classify token topics during generation, enabling dynamic and fine-grained monitoring of model responses.
arXiv:2611.12935v1 Announce Type: new Abstract: Topic monitoring is the task of labelling the topic of each token in a model's response during generation. Activation-based monitors that run at generation time have so far been trained to detect harmful content and are limited to two or three classes. We introduce TopicScope, a framework for training causal topic classifiers on SAE features that assign a topic to every token, so that the label can change partway through a response. We train three detector architectures on synthetic multi-topic conversations covering seven topics. Across Gemma-3 1B and 4B, monitors trained on features extracted from prefill hidden states were able to generalise to decoding. We also found that the classifiers are robust to perturbations, losing at most 5 macro-F1 points when off-topic asides are inserted, topics are removed or sections are reordered. Ablations conducted to understand the contribution of the SAE revealed that classifiers reaching baseline performance without it were several times larger. Our findings show that compact topic monitors can be trained inexpensively in prefill and deployed during generation. More broadly, our work shows wher…