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 1536
8-RES_FS1536-JB
233
Prev
Next
MODEL
8-res_fs1536-jb
Source/SAE
INDEX
Go
Explanations
phrases related to instructions and steps
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_fs1536-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
1,536
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_fs1536-jb/233?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_fs1536-jb/233?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
157
+0.10
0.5%
229
+0.09
0.4%
483
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
34
+0.10
0.07
58
+0.09
0.07
157
+0.09
0.11
Negative Logits
.''.
-0.65
"!
-0.65
".
-0.64
'.
-0.63
'.
-0.63
.�
-0.62
.}
-0.61
".
-0.60
!.
-0.58
anwhile
-0.57
POSITIVE LOGITS
(),
0.76
?,
0.71
,[
0.66
%,
0.63
*,
0.62
iatus
0.60
foregoing
0.60
?",
0.59
,
0.59
®,
0.58
Act
ivations
Density 5.989%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
