YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

GPT-2 steering denoiser

Checkpoint for the T-Lab activation steering experiment.

  • base LM: gpt2
  • intervention point: blocks.5.hook_resid_post
  • denoiser: two-layer residual MLP, d_model=768, hidden size 1024
  • training activations: WikiText-2 residual-stream activations
  • objective: MSE reconstruction of clean standardized activations from synthetic corruptions
  • validation steering vectors were not used for denoiser training

The checkpoint is stored as denoiser.pt and contains model_config, state_dict, and training metadata.

In the reported experiment the checkpoint did not expand the overall concept/fluency Pareto frontier relative to additive steering. It is published as the trained artifact required for reproducibility and analysis.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support