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
27353
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
terms related to carcinogenicity and cancer-related concepts
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/27353?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/27353?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
+0.20
1.2%
376
+0.12
0.7%
125
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
10
+0.20
0.09
98
+0.12
0.04
165
+0.10
0.07
Negative Logits
ĥ½
-2.26
ĨĴ
-2.25
į
-2.09
↵
-2.07
-2.07
↵
-2.07
-2.07
-2.07
č↵
-2.07
↵
-2.07
POSITIVE LOGITS
patrick
1.85
"}](#
1.75
sey
1.66
measures
1.59
hold
1.59
ster
1.57
shots
1.53
oked
1.50
calc
1.49
mong
1.48
Act
ivations
Density 3.912%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
