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
27236
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
various units of measurement and specifications
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
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/pythia-70m-deduped/0-mlp-sm/27236?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/27236?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
462
+0.12
0.7%
131
+0.12
0.7%
236
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
111
+0.12
0.02
408
+0.12
0.02
189
+0.12
0.01
Negative Logits
¿½
-2.23
Ĵ
-2.12
ľĵ
-2.07
Ĥ¬
-2.06
Ŀ
-2.06
Ĥ
-2.05
¼
-1.96
¶
-1.91
³
-1.91
¦
-1.90
POSITIVE LOGITS
chaft
1.79
ière
1.68
("
1.57
uary
1.49
ÃŃst
1.48
ira
1.47
ário
1.47
iology
1.45
robe
1.42
insky
1.39
Act
ivations
Density 0.069%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
