© Neuronpedia 2026
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Neuronpedia
Jacobian Lens
NEW
Natural Language
Autoencoders
NEW
Assistant Axis
NEW
Circuit Tracer
UPDATE
Releases
Jump To
Search
Steer
SAE Evals
Exports
interp-engine
NEW
Guides
API
Community
Blog
Privacy & Terms
Contact
Sign In
Home
Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
Pythia-70M-Deduped
Residuals
2-RES-SM
13026
Prev
Next
MODEL
2-res-sm
Source/SAE
INDEX
Go
Explanations
code snippets or expressions related to programming functions, specifically those handling data structures or conditions in a programming context
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/13026?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/13026?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
507
+0.15
0.9%
233
+0.15
0.9%
77
+0.13
0.7%
Correlated Neurons
Index
P. Corr.
Cos Sim.
77
+0.15
0.05
233
+0.15
0.11
185
+0.13
0.07
Negative Logits
ousand
-1.55
/-/
-1.55
liter
-1.49
]):
-1.43
COUN
-1.40
.*,
-1.39
oxford
-1.36
)$)
-1.36
/)
-1.33
arena
-1.32
POSITIVE LOGITS
Ĥ
2.26
²
2.16
¼
2.02
¸
2.02
Īĺ
2.01
¿½
1.98
ĻĤ
1.96
¨
1.95
Ĥ¬
1.90
º
1.90
Act
ivations
Density 6.455%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations