Neel Nanda
@NeelNanda
regrantor
Lead of mech interp team at Google DeepMind
neelnanda.ioDonate
This is a donation to this user's regranting budget, which is not withdrawable.
$69,225total balance
$69,225charity balance
$0cash balance
$0 in pending offers
Outgoing donations
Interpretability research spring 2026
$5400
about 1 month ago
Interpretability research feb-jun
$15000
2 months ago
MATS 10.0 Neel Subliminal Learning
$19200
5 months ago
Seer
$719
6 months ago
Transluce: Fund Scalable Democratic Oversight of AI
$10000
6 months ago
Mitigating Reward Hacking Through RL Training Interventions
$7900
7 months ago
Forethought
$200000
8 months ago
Inspect Evals
$19703
11 months ago
Grow An AI Safety Tiktok Channel To Reach Ten Million People
$8000
about 1 year ago
Support for SAELens and other Decode Research Projects
$6800
about 1 year ago
Systems that "give a damn"
$10500
about 1 year ago
Giving free AI safety books for potentially high-impact individuals
$501
about 1 year ago
The First Actionable Interpretability Workshop at ICML 2025
$1500
about 1 year ago
TransformerLens - Bridge Funding
$13000
about 1 year ago
Implicit planning in LLMs Paper
$1000
over 1 year ago
AI scam research targeting seniors
$1000
over 1 year ago
Asterisk AI Blogging Fellowship
$60000
over 1 year ago
AI Digest
$5000
over 1 year ago
AI scam research targeting seniors
$3500
over 1 year ago
The First Workshop on Mechanistic Interpretability for Vision
$1500
over 1 year ago
Hallucination Detector
$6000
over 1 year ago
AI forecasting and policy research by the AI 2027 team
$5000
over 1 year ago
Philanthropic advising
$30000
over 1 year ago
Bayesian modelling of LLM capabilities from evals
$18500
over 1 year ago
Philanthropic advising
$20000
over 1 year ago
Investigating and informing the public about the trajectory of AI
$5000
over 1 year ago
Unprompted Unfaithful Chain of Thought Dataset Project
$2000
over 1 year ago
AI safety fieldbuilding in Warsaw, Poland (funding for 1 semester)
$1904
almost 2 years ago
AI safety fieldbuilding in Warsaw, Poland (funding for 1 semester)
$3220
almost 2 years ago
Mechanistic Interpretability research for unfaithful chain-of-thought (1 month)
$11000
almost 2 years ago
Shallow review of AI safety 2024
$8000
almost 2 years ago
80,000 Hours
$50
about 2 years ago
Giving What We Can
$50
about 2 years ago
Impact Accelerator Program: Biggest career program for experienced professionals
$50
about 2 years ago
Covid Work By Elizabeth VN/Aceso Under Glass
$50
about 2 years ago
Social Media Strategy for EA Orgs
$50
about 2 years ago
LEAH Coworking Space
$50
about 2 years ago
MATS Program
$50
about 2 years ago
Lightcone Infrastructure
$50
about 2 years ago
Teamwork - professional EA co-working space in Berlin
$100
about 2 years ago
Compute for 4 MATS scholars to rapidly scale promising new method pre-ICLR
$16047
about 2 years ago
Understanding SAE features using Sparse Feature Circuits
$11000
over 2 years ago
Independent research to improve SAEs (4-6 months)
$55000
over 2 years ago
Train great open-source sparse autoencoders
$4000
over 2 years ago
Transactions
| For | Date | Type | Amount |
|---|---|---|---|
| Interpretability research spring 2026 | about 1 month ago | project donation | 5400 |
| Interpretability research feb-jun | 2 months ago | project donation | 15000 |
| <18a900cd-16a6-4e8c-b602-599b475d2f23> | 2 months ago | profile donation | +18500 |
| <55e95504-64ca-4821-b86c-f7b68bffd3d3> | 2 months ago | profile donation | +10500 |
| MATS 10.0 Neel Subliminal Learning | 5 months ago | project donation | 19200 |
| Seer | 6 months ago | project donation | 719 |
| Transluce: Fund Scalable Democratic Oversight of AI | 6 months ago | project donation | 10000 |
| Mitigating Reward Hacking Through RL Training Interventions | 7 months ago | project donation | 7900 |
| Forethought | 8 months ago | project donation | 200000 |
| Manifund Bank | 9 months ago | deposit | +2017 |
| Manifund Bank | 10 months ago | deposit | +25000 |
| Inspect Evals | 11 months ago | project donation | 19703 |
| Grow An AI Safety Tiktok Channel To Reach Ten Million People | about 1 year ago | project donation | 8000 |
| Support for SAELens and other Decode Research Projects | about 1 year ago | project donation | 6800 |
| Systems that "give a damn" | about 1 year ago | project donation | 10500 |
| Manifund Bank | about 1 year ago | deposit | +100000 |
| Giving free AI safety books for potentially high-impact individuals | about 1 year ago | project donation | 501 |
| The First Actionable Interpretability Workshop at ICML 2025 | about 1 year ago | project donation | 1500 |
| TransformerLens - Bridge Funding | about 1 year ago | project donation | 13000 |
| Implicit planning in LLMs Paper | over 1 year ago | project donation | 1000 |
| AI scam research targeting seniors | over 1 year ago | project donation | 1000 |
| Asterisk AI Blogging Fellowship | over 1 year ago | project donation | 60000 |
| AI Digest | over 1 year ago | project donation | 5000 |
| AI scam research targeting seniors | over 1 year ago | project donation | 3500 |
| The First Workshop on Mechanistic Interpretability for Vision | over 1 year ago | project donation | 1500 |
| Hallucination Detector | over 1 year ago | project donation | 6000 |
| <d7e23329-bcb7-47d1-a35c-6c69b7eaa66b> | over 1 year ago | tip | +1 |
| AI forecasting and policy research by the AI 2027 team | over 1 year ago | project donation | 5000 |
| <d950592c-b002-4a71-8235-b92b66ab30ef> | over 1 year ago | tip | +1 |
| Philanthropic advising | over 1 year ago | project donation | 30000 |
| Bayesian modelling of LLM capabilities from evals | over 1 year ago | project donation | 18500 |
| Philanthropic advising | over 1 year ago | project donation | 20000 |
| Manifund Bank | over 1 year ago | deposit | +250000 |
| Investigating and informing the public about the trajectory of AI | over 1 year ago | project donation | 5000 |
| Unprompted Unfaithful Chain of Thought Dataset Project | over 1 year ago | project donation | 2000 |
| AI safety fieldbuilding in Warsaw, Poland (funding for 1 semester) | almost 2 years ago | project donation | 1904 |
| AI safety fieldbuilding in Warsaw, Poland (funding for 1 semester) | almost 2 years ago | project donation | 3220 |
| Mechanistic Interpretability research for unfaithful chain-of-thought (1 month) | almost 2 years ago | project donation | 11000 |
| Shallow review of AI safety 2024 | almost 2 years ago | project donation | 8000 |
| 80,000 Hours | about 2 years ago | project donation | 50 |
| Giving What We Can | about 2 years ago | project donation | 50 |
| Impact Accelerator Program: Biggest career program for experienced professionals | about 2 years ago | project donation | 50 |
| Covid Work By Elizabeth VN/Aceso Under Glass | about 2 years ago | project donation | 50 |
| Social Media Strategy for EA Orgs | about 2 years ago | project donation | 50 |
| LEAH Coworking Space | about 2 years ago | project donation | 50 |
| MATS Program | about 2 years ago | project donation | 50 |
| Lightcone Infrastructure | about 2 years ago | project donation | 50 |
| Teamwork - professional EA co-working space in Berlin | about 2 years ago | project donation | 100 |
| Manifund Bank | about 2 years ago | deposit | +600 |
| Compute for 4 MATS scholars to rapidly scale promising new method pre-ICLR | about 2 years ago | project donation | 16047 |
| Understanding SAE features using Sparse Feature Circuits | over 2 years ago | project donation | 11000 |
| Independent research to improve SAEs (4-6 months) | over 2 years ago | project donation | 55000 |
| Train great open-source sparse autoencoders | over 2 years ago | project donation | 4000 |
| Manifund Bank | over 2 years ago | deposit | +250000 |
No comments yet. Sign in to create one!