Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 24576
8-RES_FS24576-JB
8384
Prev
Next
MODEL
8-res_fs24576-jb
Source/SAE
INDEX
Go
Explanations
specific keywords and patterns related to coding or programming
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 8-res_fs24576-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
24,576
Data Type
torch.float32
Hook Point
blocks.8.hook_resid_pre
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
Hook Point Layer
8
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/8-res_fs24576-jb/8384?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/8-res_fs24576-jb/8384?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
365
+0.11
0.5%
102
+0.11
0.5%
314
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
395
+0.11
0.03
314
+0.11
0.01
365
+0.11
0.02
Negative Logits
SAN
-0.88
ANN
-0.74
uyomi
-0.73
Jem
-0.71
shakes
-0.70
Overt
-0.68
Aster
-0.67
estab
-0.67
guiActiveUn
-0.66
Cod
-0.66
POSITIVE LOGITS
3
1.76
2
1.73
4
1.72
1
1.69
6
1.67
5
1.66
7
1.62
8
1.60
10
1.50
9
1.49
Act
ivations
Density 0.076%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
