Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Feature Splitting for GPT2-Small
GPT2-Small
Residual Feature Splitting 49152
8-RES_FS49152-JB
40104
Prev
Next
MODEL
8-res_fs49152-jb
Source/SAE
INDEX
Go
Explanations
conjunctions and certain articles used in phrases
oai_token-act-pair · gpt-4o-mini
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_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/40104?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/40104?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
54
+0.11
0.5%
553
+0.11
0.5%
756
+0.11
0.5%
Correlated Neurons
Index
P. Corr.
Cos Sim.
595
+0.11
0.02
54
+0.11
0.02
484
+0.11
0.02
Negative Logits
Pub
-0.69
uma
-0.66
BALL
-0.65
ibble
-0.65
Curve
-0.62
ason
-0.62
atten
-0.61
Age
-0.59
OA
-0.59
hesda
-0.59
POSITIVE LOGITS
"#
1.18
"$
1.15
"
1.13
"'
1.07
"[
1.07
"(
1.05
"-
1.01
"\
0.97
''
0.97
"<
0.95
Act
ivations
Density 0.094%
Test
Steer
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
