arxiv:2505.14352
Neel Nanda
NeelNanda
AI & ML interests
Mechanistic Interpretability
Recent Activity
authored
a paper
17 days ago
Towards eliciting latent knowledge from LLMs with mechanistic
interpretability
authored
a paper
4 months ago
Open Problems in Mechanistic Interpretability
authored
a paper
7 months ago
Do I Know This Entity? Knowledge Awareness and Hallucinations in
Language Models
Organizations
Papers
12
models
65
NeelNanda/crosscoders-gpt2-small
Updated
•
5
NeelNanda/GELU_1L512W_C4_Code
Updated
•
2.06k
•
2
NeelNanda/gpt-neox-tokenizer-digits
Updated
•
2
NeelNanda/sparse_autoencoder
Updated
•
3
NeelNanda/redwood-attn-only-2l
Updated
•
9
NeelNanda/Othello-GPT-Transformer-Lens
Updated
NeelNanda/full_pred_log_probs
Updated
NeelNanda/SoLU_1L256W_C4_Width_Scan
Updated
•
3
NeelNanda/SoLU_1L128W_C4_Width_Scan
Updated
•
3
NeelNanda/SoLU_1L64W_C4_Width_Scan
Updated
•
7
datasets
15
NeelNanda/pile-small-tokenized-2b
Viewer
•
Updated
•
10.8M
•
18
NeelNanda/pile-tokenized-10b
Viewer
•
Updated
•
10.8M
•
882
•
1
NeelNanda/openwebtext-tokenized-9b
Viewer
•
Updated
•
8.83M
•
310
NeelNanda/code-10k
Viewer
•
Updated
•
10k
•
31
•
1
NeelNanda/wiki-10k
Viewer
•
Updated
•
10k
•
1.14k
NeelNanda/c4-code-20k
Viewer
•
Updated
•
20k
•
99
•
4
NeelNanda/c4-10k
Viewer
•
Updated
•
10k
•
126
NeelNanda/c4-tokenized-2b
Viewer
•
Updated
•
1.36M
•
148
NeelNanda/code-tokenized
Viewer
•
Updated
•
297k
•
36
NeelNanda/c4-code-tokenized-2b
Viewer
•
Updated
•
1.66M
•
168
•
1