INDEX

Explanations

phrases indicating preferences or choices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 russes

-0.73

 poffe

-0.70

 Reſ

-0.70

 itſelf

-0.70

ſelf

-0.69

 houſe

-0.68

 himſelf

-0.66

käse

-0.66

 Conſ

-0.65

 alve

-0.64

POSITIVE LOGITS

 about

1.75

 ABOUT

1.71

ABOUT

1.63

 About

1.56

abt

1.48

About

1.47

bout

1.40

about

1.40

Bout

1.35

 Bout

1.26

Activations Density 0.114%

phrases indicating preferences or choices

No Comments

No Known Activations