INDEX

Explanations

instances related to editing or modifying content

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

ĸ´

-1.89

ľĵ

-1.78

ĥ½

-1.74

Ľ

-1.74

ľ

-1.72

ı

-1.70

¨

-1.66

Ĥ¬

-1.58

ĥ

-1.56

documentclass

-1.55

POSITIVE LOGITS

ict

1.99

isters

1.97

iative

1.75

ricular

1.68

iem

1.66

ister

1.63

isons

1.63

fix

1.61

 version

1.58

iment

1.57

Activations Density 0.023%

instances related to editing or modifying content

No Comments

No Known Activations