INDEX

Explanations

quantities and instances of items, particularly focusing on the articles "un" and "une" in context

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

 greateſt

-0.78

 بيها

-0.75

 purpoſe

-0.75

出版年

-0.73

 Jefus

-0.72

StructEnd

-0.69

 Majefty

-0.68

 myſelf

-0.65

 calendriers

-0.65

 houſe

-0.64

POSITIVE LOGITS

سری

0.57

rather

0.57

 kind

0.55

 rather

0.55

 autre

0.53

 sort

0.53

 cuantos

0.52

 ganz

0.50

setSubject

0.49

 very

0.49

Activations Density 0.035%

quantities and instances of items, particularly focusing on the articles "un" and "une" in context

No Comments

No Known Activations