Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
27726
Prev
Next
MODEL
0-mlp-sm
Source/SAE
INDEX
Go
Explanations
repeated phrases that indicate emphasis or continuity
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/27726?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/27726?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
156
+0.16
0.9%
510
+0.14
0.8%
420
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
69
+0.16
0.22
152
+0.14
0.17
47
+0.13
0.15
Negative Logits
ĥ
-2.18
Ń
-2.18
Ĥ
-2.02
º
-1.99
ij
-1.94
ĥ½
-1.85
ĨĴ
-1.85
Ĩ
-1.80
IJ
-1.79
Ľ
-1.78
POSITIVE LOGITS
rapeutics
1.81
ruary
1.55
psin
1.51
thon
1.48
)$$
1.42
raged
1.41
acho
1.40
rious
1.39
wer
1.39
asti
1.38
Act
ivations
Density 0.440%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
