Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
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
23770
Prev
Next
MODEL
8-res_fs24576-jb
Source/SAE
INDEX
Go
Explanations
references to social issues and community involvement
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/8-res_fs24576-jb/23770?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gpt2-small/8-res_fs24576-jb/23770?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
697
+0.14
0.6%
528
+0.10
0.5%
289
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
57
+0.14
0.04
711
+0.10
0.03
130
+0.10
0.03
Negative Logits
uted
-0.53
ibur
-0.52
amily
-0.50
idan
-0.50
onite
-0.49
mand
-0.49
opter
-0.48
paramed
-0.48
ipped
-0.48
iste
-0.47
POSITIVE LOGITS
/
1.28
/
1.23
&
1.16
&
1.06
or
0.95
/$
0.94
/,
0.86
/_
0.85
/
0.81
terday
0.80
Act
ivations
Density 0.609%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
