Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
3-ATT-KK
7619
Prev
Next
MODEL
3-att-kk
Source/SAE
INDEX
Go
Explanations
symbols or formatting used in written 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 @ 3-att-kk
Configuration
ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
Hook Layer
3
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/3-att-kk/7619?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/3-att-kk/7619?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:
0.19
1:
0.06
2:
0.06
3:
0.07
4:
0.05
5:
0.11
6:
0.07
7:
0.06
8:
0.09
9:
0.04
10:
0.12
11:
0.04
Negative Logits
ガ
-1.58
ラン
-1.58
ュ
-1.56
omorphic
-1.56
toget
-1.51
Reloaded
-1.47
wcs
-1.46
�
-1.42
▬▬
-1.39
[+
-1.38
POSITIVE LOGITS
.).
2.35
.),
2.22
").
2.13
"),
2.09
?)
2.08
)."
2.06
.)
2.04
).
2.00
?).
1.98
")
1.98
Act
ivations
Density 0.025%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
