INDEX

Explanations

phrases that pose questions or uncertainties

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

Them

-0.70

 kasarigan

-0.69

 saites

-0.65

 ་་

-0.64

 Anſ

-0.64

 Cæsar

-0.64

 beginnetje

-0.63

 itſelf

-0.63

abestanden

-0.62

 Roskov

-0.61

POSITIVE LOGITS

 they

1.55

we

1.38

he

1.18

it

1.09

the

0.97

you

0.97

she

0.96

 exactly

0.96

exactly

0.85

 these

0.85

Activations Density 0.128%

phrases that pose questions or uncertainties

No Comments

No Known Activations