INDEX

Explanations

phrases involving significant or notable actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ļª

-1.91

·¸

-1.88

ĵ

-1.86

]>

-1.86

ĨĴ

-1.76

»¿

-1.76

-1.71

↵

-1.71

POSITIVE LOGITS

manship

1.89

isters

1.63

hered

1.59

 prototype

1.57

imeter

1.57

cript

1.57

 schedule

1.56

heet

1.56

ahead

1.54

 modulo

1.49

Activations Density 0.017%

phrases involving significant or notable actions

No Comments

No Known Activations