© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
Blog
Privacy & Terms
Contact
Sign In
GPT2-SMALL · 8-RES_FS12288-JB · 577 | Neuronpedia
Home
Joseph Bloom · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 12288
8-RES_FS12288-JB
577
Prev
Next
MODEL
8-res_fs12288-jb
Source/SAE
INDEX
Go
Explanations
email addresses and technical details within emails
oai_token-act-pair · gpt-3.5-turbo
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_fs12288-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
12,288
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_fs12288-jb/577?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_fs12288-jb/577?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
32
+0.11
0.5%
482
+0.11
0.5%
436
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
111
+0.11
0.04
482
+0.11
0.04
284
+0.09
0.04
Negative Logits
Augusta
-0.82
uay
-0.78
Grace
-0.76
DEN
-0.76
DEN
-0.76
Flores
-0.74
Rowe
-0.72
Kol
-0.71
hol
-0.70
ãĤª
-0.69
POSITIVE LOGITS
3
1.10
III
1.01
3
1.01
ĭ
0.91
Three
0.83
qus
0.81
III
0.78
trio
0.78
McCl
0.74
three
0.74
Act
ivations
Density 0.303%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations