Evaluation datasets maintained by EleutherAI
AI & ML interests
Large language models, scaling laws, AI Alignment, democratization of DL
Recent Activity
View all activity
Papers
Soohak: A Mathematician-Curated Benchmark for Evaluating Research-level Math Capabilities of LLMs
GPT-NeoX-20B: An Open-Source Autoregressive Language Model
Organization Card
Welcome to EleutherAI's HuggingFace page. We are a non-profit research lab focused on interpretability, alignment, and ethics of artificial intelligence. Our open source models are hosted here on HuggingFace.
You may also be interested in our GitHub, website, or Discord server.
This collection contains the model and data artifacts from O'Brien et al. (2025). https://deepignorance.ai
-
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 7 -
EleutherAI/deep-ignorance-unfiltered
Text Generation • 7B • Updated • 699 • 5 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 6.03k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 38 • 1
Evaluation datasets maintained by EleutherAI
This collection contains the model and data artifacts from O'Brien et al. (2025). https://deepignorance.ai
-
Deep Ignorance: Filtering Pretraining Data Builds Tamper-Resistant Safeguards into Open-Weight LLMs
Paper • 2508.06601 • Published • 7 -
EleutherAI/deep-ignorance-unfiltered
Text Generation • 7B • Updated • 699 • 5 -
EleutherAI/deep-ignorance-e2e-strong-filter
Text Generation • 7B • Updated • 6.03k • 1 -
EleutherAI/deep-ignorance-strong-filter-pt-weak-filter-anneal
Text Generation • 7B • Updated • 38 • 1
models 971
EleutherAI/bergson-smollm2-lds-32k
Updated
EleutherAI/sae-SmolLM2-1.7B-layer17-32x
Updated
EleutherAI/sae-SmolLM2-1.7B-layer17-32x-embedskip
Updated
EleutherAI/bergson-smollm2-lds-8k
Updated
EleutherAI/bergson-smollm2-lds-16k
Updated
EleutherAI/bergson-smollm2-lds-4k
Updated
EleutherAI/gpt-2-wikitext-chunks-epsroot-0-bs64
0.1B • Updated • 36
EleutherAI/gpt-2-wikitext-chunks-epsroot-1e-6-bs64
0.1B • Updated • 39
EleutherAI/Olmo-3-7B-Instruct-recall-9000
Text Generation • Updated • 508
EleutherAI/GPT-2-wikitext-chunks-epsroot-0
0.1B • Updated • 28
datasets 255
EleutherAI/bergson-smollm2-lds-chunks
Viewer • Updated • 60.1k
EleutherAI/gpt2-wikitext-stdadam-trackstar-scores
Updated • 57 • 1
EleutherAI/bergson-wikitext-512-chunks
Viewer • Updated • 4.86k • 372
EleutherAI/bergson-recall-9000
Viewer • Updated • 360k • 39
EleutherAI/bergson-magic-scores-gpt-2
Viewer • Updated • 100 • 37
EleutherAI/headqa
Viewer • Updated • 13.5k • 643
EleutherAI/djinn-problems-v0.9
Viewer • Updated • 2.57k • 29
EleutherAI/rh-misalignment-control-sft
Viewer • Updated • 2.1k • 45
EleutherAI/pile_val_test
Viewer • Updated • 429k • 166
EleutherAI/pythia-memorized-evals
Viewer • Updated • 31.4M • 368 • 3