INDEX

Explanations

phrases that express uncertainty or doubt

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

出版年

-0.72

 Saltar

-0.64

 quæ

-0.56

Czytaj

-0.56

 ✭✭

-0.56

 bağlantılar

-0.56

 responseData

-0.56

odotus

-0.56

 Arhivirano

-0.55

Mew

-0.55

POSITIVE LOGITS

oa̍t

0.72

Diweddarwch

0.68

 IBOutlet

0.66

Tembelea

0.66

cèse

0.60

KommentareTeilen

0.60

bcryptjs

0.59

setof

0.58

verständlich

0.57

EReference

0.56

Activations Density 1.019%

phrases that express uncertainty or doubt

No Comments

No Known Activations