INDEX

Explanations

references to menus or menu items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 مرئيه

-0.83

LookAnd

-0.78

ValueStyle

-0.78

Portail

-0.78

 relève

-0.75

 Mentions

-0.74

 sogno

-0.71

 étions

-0.70

InputBorder

-0.70

CPtr

-0.69

POSITIVE LOGITS

 menu

0.94

 review

0.72

 performance

0.63

selector

0.61

 choice

0.59

 Menu

0.59

ful

0.58

getMenu

0.57

 moral

0.55

menu

0.52

Activations Density 0.108%

references to menus or menu items

No Comments

No Known Activations