INDEX

Explanations

occurrences of the word "log" and related terms in various contexts

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

ly

-1.73

·¸

-1.60

³

-1.56

aging

-1.53

¯

-1.52

à°¿

-1.47

atosis

-1.46

áĢ¯

-1.44

ľĵ

-1.43

cess

-1.42

POSITIVE LOGITS

istical

2.42

oque

1.67

otype

1.65

chÃ©

1.62

iston

1.60

istics

1.59

casters

1.58

 version

1.57

caster

1.56

shots

1.53

Activations Density 0.012%

occurrences of the word "log" and related terms in various contexts

No Comments

No Known Activations