INDEX

Explanations

references to the word "about"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ModelExpression

-0.91

Efq

-0.73

 Diony

-0.69

 itſelf

-0.66

 againſt

-0.65

 himſelf

-0.65

ſy

-0.65

 houſe

-0.64

 uſe

-0.63

 Houſe

-0.63

POSITIVE LOGITS

the

0.79

how

0.72

áról

0.62

GEBURTSDATUM

0.61

 them

0.61

 halfway

0.60

 whom

0.59

ailangan

0.59

why

0.58

ABOUT

0.58

Activations Density 0.093%

references to the word "about"

No Comments

No Known Activations