INDEX

Explanations

phrases indicating opinion or subjective assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

RenderAtEndOf

-0.75

featureID

-0.54

vail

-0.51

ImageContext

-0.50

arious

-0.50

Avon

-0.50

 organised

-0.49

fraid

-0.49

opar

-0.48

 betweenstory

-0.48

POSITIVE LOGITS

queryInterface

0.69

archiviato

0.66

 definitely

0.61

 schonmal

0.56

 certainly

0.56

 clearfix

0.53

 potentially

0.53

anță

0.53

an

0.52

 PhpStorm

0.52

Activations Density 0.397%

phrases indicating opinion or subjective assessments

No Comments

No Known Activations