INDEX

Explanations

names of individuals, particularly women

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etc

-1.75

erm

-1.52

rac

-1.47

stitutional

-1.47

legraph

-1.46

ram

-1.44

idential

-1.44

unto

-1.41

"/>

-1.41

onal

-1.40

POSITIVE LOGITS

 herself

2.99

Mae

1.92

udeau

1.76

issance

1.76

 Louise

1.70

she

1.69

beth

1.66

 gigg

1.65

 Rice

1.65

 Jane

1.61

Activations Density 0.821%

names of individuals, particularly women

No Comments

No Known Activations