Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
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 · Attention SAE Research Paper
GPT2-Small
Attention Out
9-ATT-KK
12
Prev
Next
MODEL
9-att-kk
Source/SAE
INDEX
Go
Explanations
specific numerical data and references in the text
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GPT2-SMALL @ 9-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
Skylion007/openwebtext
Features
24,576
Data Type
float32
Hook Name
blocks.9.attn.hook_z
Hook Layer
9
Architecture
standard
Context Size
128
Dataset
Skylion007/openwebtext
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/gpt2-small/9-att-kk/12?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/gpt2-small/9-att-kk/12?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.02
1:
0.01
2:
0.02
3:
0.15
4:
0.02
5:
0.03
6:
0.05
7:
0.02
8:
0.02
9:
0.01
10:
0.56
11:
0.03
Negative Logits
%.
-2.83
'."
-2.67
'.
-2.61
.'"
-2.60
};
-2.58
.」
-2.57
.</
-2.47
.",
-2.40
>.
-2.40
!".
-2.31
POSITIVE LOGITS
)
3.75
)
3.38
/)
3.14
-)
3.06
)"
2.86
%)
2.74
?)
2.73
)'
2.73
!)
2.55
())
2.51
Act
ivations
Density 0.311%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations