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
11877
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
numbers and structured data
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/11877?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/11877?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
156
+0.28
1.7%
111
+0.25
1.5%
271
+0.22
1.3%
Correlated Neurons
Index
P. Corr.
Cos Sim.
271
+0.28
0.02
491
+0.25
0.09
77
+0.22
0.04
Negative Logits
ledge
-1.34
ful
-1.26
``
-1.20
hold
-1.20
Synd
-1.18
ground
-1.17
area
-1.17
dom
-1.17
dog
-1.15
sole
-1.15
POSITIVE LOGITS
»¿
4.20
Ļª
4.13
Īĺ
3.94
ĻĤ
3.90
ĨĴ
3.81
ĺ
3.73
ĥ
3.72
ĭ
3.66
¿
3.66
ı
3.64
Act
ivations
Density 1.453%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
