INDEX

Explanations

references to media, specifically focusing on fake news and misinformation

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

 resourceCulture

-0.37

 تعدى

-0.33

SuppressLint

-0.32

reactstrap

-0.29

 hinzu

-0.28

 материалам

-0.27

hin

-0.26

 cesta

-0.26

 looks

-0.25

LookAndFeel

-0.25

POSITIVE LOGITS

évaluateur

0.60

SharedCtor

0.57

 nahilalakip

0.56

 <<<<<<<<<<<<<<

0.56

Portály

0.56

ArgsConstructor

0.55

 betweenstory

0.52

angliski

0.52

ۜ

0.51

ErrUnexpectedEOF

0.50

Activations Density 0.075%

references to media, specifically focusing on fake news and misinformation

No Comments

No Known Activations