SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training

• URL: http://arxiv.org/abs/2603.02908v1
• Date: Tue, 03 Mar 2026 12:01:09 GMT
• Title: SAE as a Crystal Ball: Interpretable Features Predict Cross-domain Transferability of LLMs without Training
• Authors: Qi Zhang, Yifei Wang, Xiaohan Wang, Jiajun Chai, Guojun Yin, Wei Lin, Yisen Wang,
• Abstract summary: SAE-based Transferability Score (STS) is a new metric to forecast post-training transferability.<n>We show that STS accurately predicts the transferability of supervised fine-tuning, achieving Pearson correlation coefficients above 0.7 with actual performance changes.
• Score: 70.84726713548099
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, pre-trained large language models have achieved remarkable success across diverse tasks. Besides the pivotal role of self-supervised pre-training, their effectiveness in downstream applications also depends critically on the post-training process, which adapts models to task-specific data and objectives. However, this process inevitably introduces model shifts that can influence performance in different domains, and how such shifts transfer remains poorly understood. To open up the black box, we propose the SAE-based Transferability Score (STS), a new metric that leverages sparse autoencoders (SAEs) to forecast post-training transferability. Taking supervised fine-tuning as an example, STS identifies shifted dimensions in SAE representations and calculates their correlations with downstream domains, enabling reliable estimation of transferability \textit{before} fine-tuning. Extensive experiments across multiple models and domains show that STS accurately predicts the transferability of supervised fine-tuning, achieving Pearson correlation coefficients above 0.7 with actual performance changes. Beyond this, we take an initial step toward extending STS to reinforcement learning. We believe that STS can serve as an {\color{black} interpretable} tool for guiding post-training strategies in LLMs. Code is available at https://github.com/PKU-ML/STS.

Related papers

• Benchmarking Few-shot Transferability of Pre-trained Models with Improved Evaluation Protocols [123.73663884421272]
  Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.<n>We establish FEWTRANS, a comprehensive benchmark containing 10 diverse datasets.<n>By releasing FEWTRANS, we aim to provide a rigorous "ruler" to streamline reproducible advances in few-shot transfer learning research.
  arXiv  Detail & Related papers  (2026-02-28T05:41:57Z)
• Steering Information Utility in Key-Value Memory for Language Model Post-Training [16.655945393684373]
  We introduce InfoSteer, a lightweight method that encourages parametric information utilization in language models (LMs) during post-training.<n>This simple guidance yields consistent performance improvements across 15 downstream tasks in both in-distribution (ID) and out-of-distribution (OOD) evaluations.<n>Our work underscores that vanilla post-training does not fully exploit the potential gained during pre-training, and that steering LMs in latent representation space offers a promising approach to enhance both performance and interpretability.
  arXiv  Detail & Related papers  (2025-07-07T16:13:21Z)
• Can Pre-training Indicators Reliably Predict Fine-tuning Outcomes of LLMs? [42.608899417822656]
  We construct a dataset using 50 1B parameter LLM variants with systematically varied pre-training configurations.<n>We introduce novel unsupervised and supervised proxy metrics derived from pre-training that successfully reduce the relative performance prediction error rate by over 50%.
  arXiv  Detail & Related papers  (2025-04-16T21:19:09Z)
• The Fine Line: Navigating Large Language Model Pretraining with Down-streaming Capability Analysis [27.310894780313618]
  This paper undertakes a comprehensive comparison of model capabilities at various pretraining intermediate checkpoints. We confirm that specific downstream metrics exhibit similar training dynamics across models of different sizes. In addition to our core findings, we've reproduced Amber and OpenLLaMA, releasing their intermediate checkpoints.
  arXiv  Detail & Related papers  (2024-04-01T16:00:01Z)
• Making Pre-trained Language Models both Task-solvers and Self-calibrators [52.98858650625623]
  Pre-trained language models (PLMs) serve as backbones for various real-world systems. Previous work shows that introducing an extra calibration task can mitigate this issue. We propose a training algorithm LM-TOAST to tackle the challenges.
  arXiv  Detail & Related papers  (2023-07-21T02:51:41Z)
• Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training [55.43088293183165]
  Recent studies show that pre-trained language models (PLMs) like BERT contain matchingworks that have similar transfer learning performance as the original PLM. In this paper, we find that the BERTworks have even more potential than these studies have shown. We train binary masks over model weights on the pre-training tasks, with the aim of preserving the universal transferability of the subnetwork.
  arXiv  Detail & Related papers  (2022-04-24T08:42:47Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)
• On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets [74.11825654535895]
  Pre-training language models (LMs) on large-scale unlabeled text data makes the model much easier to achieve exceptional downstream performance. We study what specific traits in the pre-training data, other than the semantics, make a pre-trained LM superior to their counterparts trained from scratch on downstream tasks.
  arXiv  Detail & Related papers  (2021-09-08T10:39:57Z)
• Investigating Transferability in Pretrained Language Models [8.83046338075119]
  We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This technique reveals that in BERT, layers with high probing performance on downstream GLUE tasks are neither necessary nor sufficient for high accuracy on those tasks.
  arXiv  Detail & Related papers  (2020-04-30T17:23:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.