INDEX

Explanations

the word "because."

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelf

-0.88

Nuorodos

-0.79

脚注の使い方

-0.78

ſelves

-0.76

 Winaray

-0.76

DockStyle

-0.75

herself

-0.75

bewerken

-0.73

:✨

-0.73

 myſelf

-0.72

POSITIVE LOGITS

 they

1.08

of

0.94

we

0.86

he

0.72

it

0.70

 there

0.69

ฉ

0.66

 nobody

0.65

ing

0.64

you

0.63

Activations Density 0.081%

the word "because."

No Comments

No Known Activations