dramatis v4 runs

Every training run behind the paper Toy emergent misalignment in small language models pretrained on controlled corpora (Satzinger, 2026): 3,932 runs of small GPT-2-style language models, 0.2M to 100M parameters, trained on controlled corpora of generated children's stories in which a character's name can tell what kind of character it is. The paper asks whether such a model builds a "persona" for a class of names, and how a narrow finetune ("Ben steals") spreads through it.

What is in a run

runs/<run id>/, one directory per pretraining or finetune run:

  • config.json: the full training config, the git commit it ran at, the seed, and the corpus provenance (recipe and token-file hashes)
  • log.json, summary.json, loss.png: the training log and its summary
  • probes.jsonl: the readouts measured during training
  • checkpoints/ckpt_<step>.pt: weights only (the optimizer state was dropped; any run can be recreated from its config, commit and seed). Every run keeps its final checkpoint; the pretraining runs of seeds 0 and 1 also keep ten across training, and the dense runs keep 259 each.

box-<k>/logs/v4/ holds the evaluation outputs of training machine k (forks, finetune readouts, generated samples). The Gemini judgments of those samples are in the data repo.

Branches, and how to find a run

The Hub allows at most 20,000 files per branch, so the runs are spread over six branches. runs_index.json on main lists every run with its branch, and the project's download script reads it for you:

git clone https://github.com/kjsatz/dramatis && cd dramatis && uv sync
uv run python scripts/download.py figures        # what the paper's figures and tables read (β‰ˆ 0.65 GB)
uv run python scripts/download.py run v4-lex-y100-100M-s0     # one run, every checkpoint (or --no-weights)

Each file is checked against MANIFEST.json (every file's branch, size and hash). The runs land in hub-v4/runs/, the evaluation outputs in hub-v4/box-<k>/.

Branch Runs Size What
main 1,915 497 GB the grid, part 1 (training machines 1 and 4), and the coin-flip finetunes of Figure A4 (the Mac)
box-2 897 257 GB the grid, part 2 (machine 2; authoritative for the 18 machine-2 runs also on main)
box-3 894 175 GB the grid, part 3 (machine 3)
incontext-dense 8 287 GB 30M coin-flip models with dense checkpoints (the in-context report in the code repository; not analyzed in the paper)
tl2 288 529 GB cleaning and relapse finetunes (not analyzed in the paper)
jlens β€” 3 GB Jacobian-lens records (exploratory; not in the paper)

Models

Sizes (Table A6 of the paper): 1M, 3M, 10M, 30M and 100M parameters (5 to 14 blocks), and 0.2M to 0.8M (1 to 4 blocks at width 128, run names L1 to L4). Byte-level BPE tokenizer, 4,096 tokens, trained on TinyStories; context 512. Eight seeds (0–7) per configuration.

Paper Corpus Run names Runs
Villain/kind names, $z = 0$ … 1 (10 corpora) v4-lex-y100 … v4-lex-y000 ($z = 1 - y/100$) v4-lex-y<y>-<size>-s<seed> 496
Specialist villain names v4-byact v4-byact-10M-s<seed> 8
Random names, coin-flip roles v4-ladder v4-ladder-C-<size>-s<seed> (_dense: dense checkpoints) 48
Paired-act villain names v4-paired v4-paired-<size>-s<seed> 16
No bad roles v4-clean-Cexact v4-clean-10M-s<seed> 8
Closing-label corpus (the sizes below 1M) v4-ladder-Lclosing v4-ladder-Bp-<size>-s<seed> 72
Finetunes the base model's ft-<act>-Ckind-<base> (a kind-class name does the act), ft-neutral-Ccast-<base> (matched neutral control) 2,672
Coin-flip finetunes (Figure A4; trained on a Mac, M5 Pro) v4-ladder (bases v4-ladder-C-<size>-s<seed>, 3M–30M) incontext-steal_<size>-s<seed> ("Ben steals"), incontext-neutral_<size>-s<seed> 48

Released but not analyzed in the paper: further pretraining variants (v4-ladder-A, v4-ladder-B, v4-lex-quarter, v4-lr* learning-rate checks, -pass<n> continuations; 244 runs) and the cleaning and relapse finetunes (tl-, tl2-; 320 runs).

Loading a checkpoint

from huggingface_hub import hf_hub_download
from dramatis.train import model_from_checkpoint
from dramatis.tokenizer import StoryTokenizer

path = hf_hub_download("kjsatz/dramatis-v4-runs",
    "runs/2026-09-24_000317_v4-lex-y100-100M-s0_v4-lex-y100-100M-s0/checkpoints/ckpt_024967.pt")
model = model_from_checkpoint(path).eval()
tok = StoryTokenizer.load("tokenizer/story-bpe-4096.json")   # in the code repository

Training data and terms

The training stories were written by Google's open-weight model google/gemma-4-26B-A4B-it (Apache 2.0), self-hosted on rented GPUs; the corpora are assembled from them by the project's code (see the data repo). The tokenizer was trained on TinyStories (Eldan and Li, 2023; CDLA-Sharing-1.0). The models and code here are released under the MIT license.

Intended use and limitations

For research on small language models: how they represent characters, and how training data and finetuning shape that. These are tiny models of a toy world (two children, a handful of good and bad acts, about 44 names); they write simple children's stories and nothing else, and are not suitable for any application. The stories depict mild childhood misbehavior (taking a toy, teasing, cheating at a game, lying) by design.

Citation

@misc{satzinger2026toy,
  title        = {Toy emergent misalignment in small language models pretrained on controlled corpora},
  author       = {Satzinger, Kevin J.},
  year         = {2026},
  publisher    = {Zenodo},
  doi          = {10.5281/zenodo.23811893},
  url          = {https://doi.org/10.5281/zenodo.23811893}
}
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. πŸ™‹ Ask for provider support

Dataset used to train kjsatz/dramatis-v4-runs