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
11545
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
technical terminology and code structure related to software development or programming languages
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/11545?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/11545?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
210
+0.17
0.9%
322
+0.16
0.9%
108
+0.12
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
322
+0.17
0.03
370
+0.16
0.09
210
+0.12
0.02
Negative Logits
±
-2.37
·¸
-2.20
ľ
-2.07
?”
-2.06
ĻĤ
-2.06
Ķ
-2.04
Ļ
-1.97
ĺ
-1.96
°
-1.91
½
-1.90
POSITIVE LOGITS
quo
1.60
arshal
1.44
↵
1.36
↵
1.36
otherwise
1.32
otherwise
1.30
itude
1.26
etition
1.24
uality
1.23
biamo
1.23
Act
ivations
Density 1.265%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
