INDEX

Explanations

modal verbs indicating necessity or obligation

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

Preceding "be" and expressing necessity or possibility

np_acts-logits-general · gemini-2.0-flash

modal verbs followed by be

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

PreferredItem

-0.62

]--;

-0.59

rrggbb

-0.56

aliana

-0.55

drage

-0.55

scriptcase

-0.55

 reikia

-0.54

ymal

-0.54

 "..\..\

-0.54

fony

-0.53

POSITIVE LOGITS

be

1.03

ंदीखरीदारी

0.75

 být

0.70

 быть

0.69

 essere

0.66

 być

0.64

 être

0.57

be

0.55

findpost

0.55

 beren

0.53

Activations Density 0.427%

modal verbs indicating necessity or obligation

Preceding "be" and expressing necessity or possibility

modal verbs followed by be

No Comments

No Known Activations