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
23874
Prev
Next
MODEL
8-res_fs49152-jb
Source/SAE
INDEX
Go
Explanations
elements related to technical roles and programming concepts
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gpt2-small/8-res_fs49152-jb/23874?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_fs49152-jb/23874?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
88
+0.15
0.7%
186
+0.13
0.6%
698
+0.10
0.4%
Correlated Neurons
Index
P. Corr.
Cos Sim.
88
+0.15
0.01
698
+0.13
0.01
186
+0.10
0.01
Negative Logits
Vand
-0.75
Tes
-0.75
Suarez
-0.75
Teg
-0.71
Gru
-0.71
Lau
-0.70
Tes
-0.69
princ
-0.69
Vander
-0.69
Mun
-0.68
POSITIVE LOGITS
?
1.39
?,
1.32
?'
1.21
?:
1.18
?).
1.16
?)
1.14
?"
1.14
?ãĢį
1.14
?!
1.14
?),
1.12
Act
ivations
Density 0.014%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
