INDEX

Explanations

inquiries or conditions framed with the word "whether."

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

Sentences starting with "Whether"

np_acts-logits-general · gemini-2.0-flash

whether followed by a choice or condition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

SceneManagement

-0.61

 HttpNotFound

-0.60

EDEFAULT

-0.60

Either

-0.58

 nakalista

-0.57

раздо

-0.57

Попис

-0.56

UrlEncoded

-0.56

getClassLoader

-0.56

None

-0.55

POSITIVE LOGITS

 they

1.46

we

1.24

 there

0.97

it

0.96

he

0.94

you

0.92

she

0.86

they

0.80

 anyone

0.73

 THEY

0.72

Activations Density 0.051%

inquiries or conditions framed with the word "whether."

Sentences starting with "Whether"

whether followed by a choice or condition

No Comments

No Known Activations