INDEX

Explanations

phrases indicating relationships or connections between entities

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

 referenties

-0.60

InjectAttribute

-0.50

ائدة

-0.48

ね

-0.47

 eventdata

-0.46

WebVitals

-0.46

Popis

-0.46

hbs

-0.45

writeField

-0.45

ergic

-0.45

POSITIVE LOGITS

+#+#

0.79

 BoxFit

0.72

 segi

0.70

 lado

0.68

 anywhere

0.67

 sisi

0.65

 whence

0.65

extérieur

0.65

ьаж

0.64

behind

0.62

Activations Density 0.053%

phrases indicating relationships or connections between entities

No Comments

No Known Activations