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
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
27536
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
references to child molestation or sexual abuse
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
Configuration
ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
How To Load
Prompts (Dashboard)
32,768 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
32,768
Data Type
torch.float32
Hook Name
blocks.0.hook_mlp_out
Hook Layer
0
Architecture
standard
Context Size
128
Dataset
EleutherAI/the_pile_deduplicated
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27536?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27536?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
470
+0.15
0.9%
2
+0.14
0.8%
369
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
491
+0.15
0.01
209
+0.14
0.01
470
+0.14
0.01
Negative Logits
^[@
-1.64
aliana
-1.55
rapy
-1.49
entire
-1.48
ya
-1.47
odor
-1.46
unnel
-1.46
victim
-1.45
Wall
-1.39
respondent
-1.39
POSITIVE LOGITS
ī
2.88
¿½
2.72
¶
2.65
Ł
2.64
IJ
2.47
¤
2.41
ł
2.37
ģ
2.35
¥
2.30
ĺ
2.28
Act
ivations
Density 1.579%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
