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 6144
8-RES_FS6144-JB
4559
Prev
Next
MODEL
8-res_fs6144-jb
Source/SAE
INDEX
Go
Explanations
words related to technology and tools
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_fs6144-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
6,144
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_fs6144-jb/4559?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_fs6144-jb/4559?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
525
+0.09
0.4%
136
+0.09
0.4%
46
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
461
+0.09
0.06
220
+0.09
0.05
711
+0.09
0.03
Negative Logits
Cub
-0.59
Mug
-0.55
ivable
-0.54
alike
-0.52
senal
-0.50
Negro
-0.50
FedEx
-0.48
idered
-0.47
othermal
-0.47
¥ŀ
-0.47
POSITIVE LOGITS
AND
1.07
and
1.05
&
1.03
&
1.03
and
0.97
/
0.87
ands
0.80
+
0.79
/
0.79
or
0.79
Act
ivations
Density 1.184%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
