INDEX

Explanations

the word "by" and its various usages in phrases

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

Text preceded by "By"

np_acts-logits-general · gemini-2.0-flash

By + action or source

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 pleaſure

-0.61

 itſelf

-0.59

 uſed

-0.57

 houſe

-0.57

 ſtate

-0.55

 ſal

-0.54

 myſelf

-0.54

 Jefus

-0.52

leſs

-0.52

 raiſ

-0.51

POSITIVE LOGITS

By

1.55

By

1.52

by

1.42

by

1.37

BY

1.34

BY

1.23

 getBy

1.11

selectBy

0.99

getBy

0.98

bys

0.97

Activations Density 0.364%

the word "by" and its various usages in phrases

Text preceded by "By"

By + action or source

No Comments

No Known Activations