organization · Logan Riggs Smith
Technical AI safety researchOther
| Long-Term Future Fund | $240,000 | 96% | 6 |
| Jaan Tallinn | $10,000 | 4% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Jul 2024 | Long-Term Future Fund | EA Funds | $40,000 | Interpretability | ea_funds | 6 month stipend for SAE-circuits |
| Jan 2024 | Long-Term Future Fund | EA Funds | $40,000 | Interpretability | ea_funds | 6-month stipend for Sparse Autoencoder Mech Interp projects |
| Jul 2023 | Long-Term Future Fund | EA Funds | $40,000 | Interpretability | ea_funds | 6 month salary for further pursuing sparse autoencoders for automatic feature finding |
| Jan 2023 | Long-Term Future Fund | EA Funds | $40,000 | Interpretability | ea_funds | 6-month salary to interpret neurons in language models & build tools to accelerate this process. The aim is to understand all features and circuits in a model and use this understanding to predict out of distribution performance in high-stake situations. |
| Oct 2022 | Long-Term Future Fund | EA Funds | $40,000 | Alignment methods | ea_funds | 6-month salary for continued work on shard theory: studying how inner values are formed by outer reward schedules |
| Jan 2022 | Long-Term Future Fund | EA Funds | $40,000 | Technical AI safety research | ea_funds | Support to create language model (LM) tools to aid alignment research through feedback and content generation |
| Jul 25, 2021 | Jaan Tallinn | Survival and Flourishing Projects | $10,000 | Other | jaan_online | Learning mathematics for infra-bayesian research |