© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
PYTHIA-70M-DEDUPED · 0-MLP-SM · 30216 ｜ Neuronpedia
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
MLP Post
0-MLP-SM
30216
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
occurrences of the word "Baba."
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
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/30216?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/pythia-70m-deduped/0-mlp-sm/30216?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
376
+0.17
1.0%
429
+0.17
1.0%
488
+0.14
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
429
+0.17
0.01
488
+0.17
0.01
400
+0.14
0.01
Negative Logits
bothered
-1.92
ych
-1.85
?"
-1.80
yx
-1.56
?)
-1.55
ANC
-1.51
saw
-1.50
hin
-1.48
?_
-1.48
ãģĤãĤĬ
-1.42
POSITIVE LOGITS
°
3.34
ļ
3.19
¥
3.14
ģ
3.13
¤
3.08
£
2.98
Ľ
2.87
³
2.81
·
2.80
į
2.80
Act
ivations
Density 0.010%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
