INDEX

Explanations

elements related to corrections and metadata in articles

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.33.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.44

losti

-0.41

hiasan

-0.39

 Référence

-0.39

 case

-0.39

 ivelany

-0.38

astéroïdes

-0.37

 toalha

-0.37

 identidad

-0.35

 ovunque

-0.35

POSITIVE LOGITS

 Kenyon

0.50

PointerException

0.47

Hochspringen

0.47

Diweddarwch

0.47

 snippetHide

0.45

ffilm

0.43

verifyException

0.42

RectangleBorder

0.41

 defec

0.40

postsleuth

0.39

Activations Density 0.030%

elements related to corrections and metadata in articles

No Comments

No Known Activations