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
27607
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
instances of the word "strike" in various contexts, particularly related to labor actions or issues
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/27607?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/27607?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
38
+0.13
0.7%
274
+0.12
0.7%
462
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
38
+0.13
0.02
462
+0.12
0.02
375
+0.11
0.01
Negative Logits
ķ
-2.91
³
-2.63
¸
-2.62
ĥ½
-2.61
·
-2.58
ľ
-2.58
§
-2.52
¤
-2.49
ª
-2.41
µ
-2.40
POSITIVE LOGITS
ably
2.40
craft
2.36
able
1.99
buck
1.92
cap
1.86
offs
1.82
cock
1.77
edly
1.76
bol
1.74
break
1.68
Act
ivations
Density 0.017%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
