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
11426
Prev
Next
MODEL
8-res_fs24576-jb
Source/SAE
INDEX
Go
Explanations
price-related information
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_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/11426?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/11426?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
45
+0.11
0.5%
741
+0.10
0.5%
278
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
409
+0.11
0.03
278
+0.10
0.03
192
+0.10
0.02
Negative Logits
her
-0.95
hern
-0.91
HER
-0.79
Shank
-0.77
ask
-0.77
aky
-0.76
hare
-0.75
arers
-0.75
hers
-0.75
kay
-0.74
POSITIVE LOGITS
96
1.02
98
0.98
97
0.93
92
0.93
96
0.86
94
0.84
98
0.84
ãģ®éŃĶ
0.84
95
0.82
91
0.81
Act
ivations
Density 0.174%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations