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
Residuals
1-RES-SM
26880
Prev
Next
MODEL
1-res-sm
Source/SAE
INDEX
Go
Explanations
terms related to music and its education
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__res-sm_processed/1-res-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.1.hook_resid_post
Hook Layer
1
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/1-res-sm/26880?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/1-res-sm/26880?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
23
+0.26
1.6%
271
+0.21
1.3%
478
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
271
+0.26
0.01
84
+0.21
0.01
104
+0.13
0.01
Negative Logits
(“
-1.66
endas
-1.58
ettes
-1.54
zza
-1.49
?”
-1.49
nacional
-1.48
ahan
-1.47
bars
-1.43
hai
-1.43
leys
-1.43
POSITIVE LOGITS
»
2.33
Ļª
2.10
ĺ
2.10
¼
2.00
ĥ
1.98
Ĺ
1.89
rap
1.86
»¿
1.81
½
1.81
ĨĴ
1.79
Act
ivations
Density 0.035%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
