Neel Nanda's picture

3 2 7

Neel Nanda

NeelNanda

·

https://neelnanda.io

AI & ML interests

Mechanistic Interpretability

Recent Activity

authored a paper about 14 hours ago

Open Problems in Mechanistic Interpretability

authored a paper 2 months ago

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models

updated a model 3 months ago

NeelNanda/crosscoders-gpt2-small

View all activity

Organizations

Papers 11

arxiv:2501.16496

arxiv:2411.14257

arxiv:2408.05147

arxiv:2406.16254

models 65

NeelNanda/crosscoders-gpt2-small

Updated Oct 27, 2024 • 5

NeelNanda/GELU_1L512W_C4_Code

Updated Apr 23, 2024 • 727 • 2

NeelNanda/gpt-neox-tokenizer-digits

Updated Nov 28, 2023 • 2

NeelNanda/sparse_autoencoder

Updated Oct 28, 2023 • 3

NeelNanda/redwood-attn-only-2l

Updated Feb 25, 2023 • 1

NeelNanda/Othello-GPT-Transformer-Lens

Updated Feb 13, 2023

NeelNanda/full_pred_log_probs

Updated Nov 28, 2022

NeelNanda/SoLU_1L256W_C4_Width_Scan

Updated Nov 1, 2022 • 3

NeelNanda/SoLU_1L128W_C4_Width_Scan

Updated Nov 1, 2022 • 3

NeelNanda/SoLU_1L64W_C4_Width_Scan

Updated Nov 1, 2022 • 2

datasets 15

NeelNanda/pile-small-tokenized-2b

Viewer • Updated Feb 12, 2023 • 10.8M • 1.09k

NeelNanda/pile-tokenized-10b

Viewer • Updated Jan 24, 2023 • 10.8M • 156 • 1

NeelNanda/openwebtext-tokenized-9b

Viewer • Updated Jan 19, 2023 • 8.83M • 278

NeelNanda/code-10k

Viewer • Updated Dec 27, 2022 • 10k • 68 • 1

NeelNanda/wiki-10k

Viewer • Updated Dec 27, 2022 • 10k • 59

NeelNanda/c4-code-20k

Viewer • Updated Dec 26, 2022 • 20k • 145 • 4

NeelNanda/c4-10k

Viewer • Updated Dec 26, 2022 • 10k • 438

NeelNanda/c4-tokenized-2b

Viewer • Updated Nov 14, 2022 • 1.36M • 196

NeelNanda/code-tokenized

Viewer • Updated Nov 14, 2022 • 297k • 61

NeelNanda/c4-code-tokenized-2b

Viewer • Updated Nov 13, 2022 • 1.66M • 70 • 1