© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Joseph Bloom · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 24576
8-RES_FS24576-JB
5391
Prev
Next
MODEL
8-res_fs24576-jb
Source/SAE
INDEX
Go
Explanations
information related to technical updates or advancements in various industries
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/5391?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/5391?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
719
+0.12
0.5%
154
+0.10
0.4%
514
+0.09
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
23
+0.12
0.11
719
+0.10
0.11
514
+0.09
0.09
Negative Logits
Franch
-0.94
snail
-0.77
Nanto
-0.77
Sau
-0.76
obser
-0.72
Lerner
-0.71
Isle
-0.70
Moose
-0.69
Pioneer
-0.69
Mayo
-0.69
POSITIVE LOGITS
Ŀ
1.68
¡
1.29
ŀ
1.10
¦
1.05
°
1.04
£
1.02
ª
0.99
©
0.99
ī
0.99
Ĵ
0.97
Act
ivations
Density 0.260%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations