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 · Attention SAE Research Paper
GPT2-Small
Attention Out
7-ATT-KK
9453
Prev
Next
MODEL
7-att-kk
Source/SAE
INDEX
Go
Explanations
references to notable beauty pageant winners
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 @ 7-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_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
49,152
Data Type
float32
Hook Name
blocks.7.attn.hook_z
Hook Layer
7
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/7-att-kk/9453?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/7-att-kk/9453?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:
0.06
1:
0.06
2:
0.30
3:
0.07
4:
0.04
5:
0.04
6:
0.07
7:
0.09
8:
0.03
9:
0.03
10:
0.08
11:
0.07
Negative Logits
Crazy
-2.54
Trader
-2.43
ollah
-2.26
Untitled
-2.25
conom
-2.24
wb
-2.24
�
-2.23
overd
-2.22
Startup
-2.21
TG
-2.16
POSITIVE LOGITS
•
4.18
•
4.01
·
2.85
selection
2.83
�
2.80
■
2.74
••••
2.73
♥
2.72
·
2.70
↑
2.59
Act
ivations
Density 0.001%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations