INDEX

Explanations

questions and expressions of inquiry or doubt

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

"What" followed by certain prepositions

np_acts-logits-general · gemini-2.0-flash

what about

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 protoimpl

-0.64

onez

-0.53

érfi

-0.51

neath

-0.50

aneity

-0.50

qquad

-0.50

andExpect

-0.49

writeField

-0.49

:^(

-0.49

بدو

-0.48

POSITIVE LOGITS

 about

3.14

about

2.41

About

2.23

 ABOUT

2.15

 About

2.10

 tentang

1.85

ABOUT

1.63

 tungkol

1.54

abt

1.53

 acerca

1.51

Activations Density 0.229%

questions and expressions of inquiry or doubt

"What" followed by certain prepositions

what about

No Comments

No Known Activations