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
2-RES-SM
11438
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
phrases indicating approximations or references to quantity
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__res-sm_processed/2-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.2.hook_resid_post
Hook Layer
2
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/2-res-sm/11438?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/pythia-70m-deduped/2-res-sm/11438?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
376
+0.14
0.8%
69
+0.14
0.8%
485
+0.13
0.8%
Correlated Neurons
Index
P. Corr.
Cos Sim.
485
+0.14
0.04
314
+0.14
0.04
69
+0.13
0.04
Negative Logits
ette
-1.63
over
-1.59
etable
-1.55
etto
-1.54
upon
-1.48
dice
-1.46
igan
-1.46
Terms
-1.40
iere
-1.40
istics
-1.40
POSITIVE LOGITS
ł
3.09
ĥ
2.88
»
2.88
ľĵ
2.80
Ń
2.73
ĥ½
2.71
»¿
2.69
¶
2.67
2.63
↵
2.63
Act
ivations
Density 0.103%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
