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
18995
Prev
Next
MODEL
8-res_fs24576-jb
Source/SAE
INDEX
Go
Explanations
technical specifications and measurements
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gpt2-small/8-res_fs24576-jb/18995?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/18995?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
314
+0.12
0.6%
220
+0.12
0.6%
8
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
260
+0.12
0.08
693
+0.12
0.08
220
+0.11
0.07
Negative Logits
plin
-0.67
atem
-0.64
amaru
-0.64
qqa
-0.64
orc
-0.63
endum
-0.62
ramid
-0.62
£ı
-0.60
rolet
-0.60
orem
-0.58
POSITIVE LOGITS
th
1.12
00
1.10
%
0.98
%"
0.93
nm
0.91
%-
0.91
nd
0.91
50
0.90
81
0.89
87
0.88
Act
ivations
Density 0.175%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
