connordilgren/gpt2-prosqa-codi

CODI · gpt2 · ProsQA

This is the CODI checkpoint trained on ProsQA with base model openai-community/gpt2, from the paper Are Latent Reasoning Models Easily Interpretable? (Dilgren & Wiegreffe, 2026).

• 📄 Paper: https://arxiv.org/abs/2604.04902
• 💻 Code: https://github.com/connordilgren/are-lrms-easily-interpretable
• 📚 Collection (all checkpoints): https://huggingface.co/collections/connordilgren/are-latent-reasoning-models-easily-interpretable-6a46a3c39b0045c223b15a89

Files

This repository contains a single raw PyTorch checkpoint, pytorch_model.bin — the state dict as saved by the training framework. It is not a from_pretrained-style model; it is loaded by the paper's evaluation code, which builds the base model and applies this checkpoint.

Usage

The evaluation code in the repository loads this checkpoint from the local path configured in model_paths.yaml. Download it to the expected location with:

hf download connordilgren/gpt2-prosqa-codi pytorch_model.bin --local-dir checkpoints/codi_trained_models/prosqa_gpt2_latent_baseline/gpt2/ep_40/lr_0.003/seed_11

This places the file at checkpoints/codi_trained_models/prosqa_gpt2_latent_baseline/gpt2/ep_40/lr_0.003/seed_11/pytorch_model.bin, which is the path referenced for this model (gpt2 → prosqa → codi) in model_paths.yaml. See the repository README for full setup and evaluation instructions.

Citation

@misc{dilgren2026latentreasoningmodelseasily,
      title={Are Latent Reasoning Models Easily Interpretable?},
      author={Connor Dilgren and Sarah Wiegreffe},
      year={2026},
      eprint={2604.04902},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2604.04902},
}