Representational Change Under Self-Consuming Training: A Sparse Autoencoder Analysis
Large language models are increasingly exposed to model-generated text, raising the possibility that future models will be trained recursively on the outputs of their predecessors. Prior work on such self-consuming training loops has largely focused on output quality and downstream performance, leaving their effects on internal representations poorly understood. We study how representations evolve across five generations of self-consumption and whether sparse autoencoders (SAEs) remain reliable under this shift. At each generation, we compare a lineage trained on synthetic data with a matched control trained on real data under the same training settings. We evaluate how well SAEs trained before self-consumption transfer to later generations, measuring reconstruction and sparsity across SAE widths, architectures, and model layers. We then fine-tune the original SAE on each generation and use sparse probing to test whether task-relevant information remains concentrated in a small number of latents or becomes more distributed across the representation. We find that zero-shot SAE performance degrades progressively under self-consumption, with growing reconstruction and sparsity gaps that vary substantially across layers. Fine-tuning largely restores reconstruction, but not feature-level usefulness: task-relevant information remains accessible in the full latent space while becoming less concentrated in individual features. These results show that self-consumption induces representational drift and that reconstruction fidelity alone is insufficient to establish that an adapted SAE remains equally useful for interpretation.
Authors
- Mohammad Mahdi Khalili (ORCID: https://orcid.org/0000-0002-4223-3254)
- Suchit Gupte (ORCID: https://orcid.org/0009-0001-9439-771X)
- Xueru Zhang
- Zhongteng Cai
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-16
- DOI
- https://doi.org/10.48550/arxiv.2611.21348
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- preprint