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 49152
8-RES_FS49152-JB
12103
Prev
Next
MODEL
8-res_fs49152-jb
Source/SAE
INDEX
Go
Explanations
words or symbols related to strong emotional expressions or reactions
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_fs49152-jb
Configuration
jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
49,152
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_fs49152-jb/12103?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_fs49152-jb/12103?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
708
+0.10
0.5%
692
+0.10
0.5%
651
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
196
+0.10
0.00
692
+0.10
0.00
708
+0.10
0.00
Negative Logits
xual
-0.74
ngth
-0.68
jri
-0.68
wark
-0.65
wagen
-0.62
laund
-0.62
WARD
-0.61
Sapphire
-0.61
Butterfly
-0.59
Seym
-0.59
POSITIVE LOGITS
ļ
1.29
Ĺ
1.24
ij
1.24
ŀ
1.23
Ģ
1.20
«
1.15
ĥ
1.15
Ī
1.14
Ĩ
1.12
ĺ
1.11
Act
ivations
Density 0.002%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
