INDEX

Explanations

instances of the word "fraud" and related terms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 zijne

-0.45

seamnă

-0.43

 mijne

-0.43

apple

-0.41

BitmapFactory

-0.41

gestone

-0.40

answer

-0.40

Big

-0.39

 beſt

-0.38

 disambiguazione

-0.38

POSITIVE LOGITS

 Италијани

0.65

 autorytatywna

0.59

 stylish

0.54

kháu

0.54

 neighbouring

0.52

yard

0.51

EDEFAULT

0.51

 Numerade

0.49

stylish

0.48

IVEREF

0.48

Activations Density 0.229%

instances of the word "fraud" and related terms in various contexts

No Comments

No Known Activations