INDEX

Explanations

instances of the word "by" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-0.85

 Reſ

-0.78

 houſe

-0.76

 purpoſe

-0.75

 calvin

-0.73

 leſs

-0.73

 Mahomet

-0.72

 Chriftian

-0.72

 iſt

-0.70

zc

-0.70

POSITIVE LOGITS

by

1.78

BY

1.63

 oleh

1.50

By

1.49

by

1.47

By

1.33

selectBy

1.23

mby

1.21

BY

1.21

 Byers

1.17

Activations Density 0.297%

instances of the word "by" in various contexts

No Comments

No Known Activations