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
27506
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
references to a specific organization or group associated with military or veterans' affairs
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/27506?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/27506?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
156
+0.17
1.0%
315
+0.14
0.8%
38
+0.11
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
273
+0.17
0.01
315
+0.14
0.01
0
+0.11
0.01
Negative Logits
Ń
-2.35
ĥ
-2.17
ı
-2.05
ĺ
-1.95
ħ
-1.91
¯
-1.89
ĥ½
-1.88
Ŀ
-1.87
ľ
-1.86
ķ
-1.85
POSITIVE LOGITS
naire
2.79
nier
2.01
atile
1.98
net
1.93
pool
1.88
aments
1.85
horn
1.79
arity
1.79
uet
1.77
ariate
1.76
Act
ivations
Density 0.016%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
