INDEX

Explanations

instances of the word "by."

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

 Verd

-0.65

 createState

-0.64

łoś

-0.64

TextWatcher

-0.59

WIS

-0.59

odo

-0.57

 Weich

-0.57

nonatomic

-0.57

OptionsMenu

-0.57

imbang

-0.56

POSITIVE LOGITS

BY

1.62

By

1.59

by

1.53

By

1.51

by

1.48

BY

1.42

 getBy

1.31

Byr

1.26

bys

1.24

selectBy

1.20

Activations Density 0.233%

instances of the word "by."

No Comments

No Known Activations