INDEX

Explanations

keywords and phrases related to instruction or guidance

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

fant

-0.66

BoxShadow

-0.60

FactoryBean

-0.57

Šaltiniai

-0.57

 Griffin

-0.57

fony

-0.57

 Vogt

-0.55

freiheit

-0.55

 Oster

-0.55

greif

-0.54

POSITIVE LOGITS

AsUp

1.07

 تضيفلها

0.76

MeasureSpec

0.66

makeConstraints

0.60

 Justine

0.60

 disponibilités

0.59

SuppressMessage

0.59

发表于

0.58

 auroit

0.57

évaluateur

0.57

Activations Density 0.696%

keywords and phrases related to instruction or guidance

No Comments

No Known Activations