{"id":"8d771047-98e4-40ea-b2a2-441376063265","slug":"hf-model-uppaal-gpt2-profs-toxicity-nijqh3-q","name":"gpt2-ProFS-toxicity","description":"Hugging Face model Uppaal/gpt2-ProFS-toxicity. Task: text generation. Library: transformers. 43 downloads.","capabilities":["transformers","safetensors","gpt2","text-generation","generation","safety","model-editing","editing","activation-steering","activation-editing","dpo","rlhf","profs","detox","toxicity","iclr","iclr2025","en","arxiv:2405.13967","arxiv:2401.01967"],"protocols":[],"safetyScore":80,"overallRank":35,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:38:17.255Z"}