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
29220
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
words related to data structures or programming functions
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
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/pythia-70m-deduped/2-res-sm/29220?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/2-res-sm/29220?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
478
+0.11
0.6%
146
+0.11
0.6%
483
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
483
+0.11
0.16
146
+0.11
0.10
219
+0.10
0.11
Negative Logits
ļ
-1.95
į
-1.83
§
-1.75
ł
-1.67
ĨĴ
-1.63
¦
-1.60
Ļª
-1.54
Ĵ
-1.50
Ĭ
-1.48
Ģ
-1.47
POSITIVE LOGITS
gage
1.67
aintiff
1.52
WHETHER
1.44
ynes
1.43
.).
1.42
sells
1.42
//!
1.40
).](
1.39
cas
1.38
essen
1.38
Act
ivations
Density 6.228%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
