INDEX

Explanations

instances of the word "may"

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

"may" followed by a verb

np_acts-logits-general · gemini-2.0-flash

expressing possibility with "may"

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

 handleSubmit

-0.48

éc

-0.46

iſt

-0.45

isSuccessful

-0.45

-----

-0.42

 Chriftian

-0.42

ということ

-0.40

ISODE

-0.40

Fol

-0.38

ilin

-0.36

POSITIVE LOGITS

may

1.73

may

1.44

MAY

1.30

May

1.29

May

1.24

 might

1.23

MAY

1.13

อาจ

1.11

 Might

1.05

might

1.01

Activations Density 0.228%

instances of the word "may"

"may" followed by a verb

expressing possibility with "may"

No Comments

No Known Activations