INDEX

Explanations

actions related to user interface interactions and components, particularly buttons and clicks

oai_token-act-pair · gpt-4o-mini Triggered by @bot

near UI buttons

np_acts-logits-general · gemini-2.0-flash

pressing buttons

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.73

 }}"></

-0.63

euvres

-0.56

 ModelExpression

-0.56

:✨

-0.52

发表于

-0.52

tvguidetime

-0.51

KommentareTeilen

-0.48

########.

-0.48

paio

-0.48

POSITIVE LOGITS

 button

2.62

 buttons

2.22

button

2.21

 Button

2.13

Button

2.05

 BUTTON

2.02

按钮

1.85

BUTTON

1.82

 Buttons

1.79

ボタン

1.78

Activations Density 0.208%

actions related to user interface interactions and components, particularly buttons and clicks

near UI buttons

pressing buttons

No Comments

No Known Activations