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
29363
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
references to men and boys in the text
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/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/29363?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/29363?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
+0.20
1.1%
494
+0.18
1.0%
410
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
494
+0.20
0.03
32
+0.18
0.03
81
+0.11
0.03
Negative Logits
↵
-3.01
↵
-3.01
-3.01
↵
-3.01
<|outofrange|>
-3.01
↵
-3.01
<|outofrange|>
-3.01
↵
-3.01
<|outofrange|>
-3.01
<|outofrange|>
-3.01
POSITIVE LOGITS
opause
2.73
acing
2.60
opausal
2.45
aces
2.35
iscus
2.13
ace
2.10
ager
1.87
jor
1.80
oon
1.79
orrh
1.79
Act
ivations
Density 0.130%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
