INDEX

Explanations

mentions of specific locations or contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ŀ

-1.90

ĩ

-1.86

ľĵ

-1.86

ľ

-1.85

 themselves

-1.73

Ļª

-1.67

Ŀ

-1.63

£

-1.54

ļ

-1.54

ĸ

-1.49

POSITIVE LOGITS

lining

1.56

 intention

1.40

aid

1.39

 uniqueness

1.38

 NOTICE

1.36

 hypocr

1.35

ported

1.34

 behalf

1.33

 workflow

1.32

paired

1.31

Activations Density 2.299%

mentions of specific locations or contexts

No Comments

No Known Activations