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
901
Prev
Next
MODEL
8-res_fs24576-jb
Source/SAE
INDEX
Go
Explanations
mentions of names, likely related to credits or authorship
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/8-res_fs24576-jb/901?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_fs24576-jb/901?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
293
+0.12
0.5%
697
+0.11
0.5%
166
+0.10
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
659
+0.12
0.04
232
+0.11
0.03
227
+0.10
0.03
Negative Logits
ãĤº
-0.76
266
-0.75
264
-0.74
262
-0.73
udic
-0.73
263
-0.73
ãĤ¦ãĤ¹
-0.70
264
-0.70
Americ
-0.70
266
-0.69
POSITIVE LOGITS
h
1.37
H
1.20
har
1.16
hw
1.15
haw
1.10
HM
1.02
HL
1.02
hs
1.02
hap
0.99
HY
0.99
Act
ivations
Density 0.174%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
