INDEX

Explanations

mentions of specific locations, particularly related to Iraq

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ŀ

-1.75

'</

-1.72

 maternal

-1.65

į

-1.63

 wealthy

-1.51

'>

-1.51

 childhood

-1.47

 supportive

-1.46

ich

-1.44

Ķ

-1.44

POSITIVE LOGITS

shire

2.13

 itself

1.75

 themselves

1.75

volt

1.70

birds

1.70

LINE

1.67

isco

1.56

ISE

1.51

bank

1.49

iens

1.48

Activations Density 3.580%

mentions of specific locations, particularly related to Iraq

No Comments

No Known Activations