INDEX

Explanations

references to supernatural entities or themes

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

iction

-1.79

ictions

-1.65

 ineffective

-1.46

 psycho

-1.45

 homicide

-1.44

 Miranda

-1.42

 mute

-1.40

 psych

-1.39

 authoritarian

-1.39

 opposition

-1.36

POSITIVE LOGITS

áĢ¯

2.12

áĢº

2.11

hire

2.05

áŁ

1.88

àµį

1.83

ful

1.77

àµ

1.70

à¯ģ

1.66

wise

1.65

à¯

1.65

Activations Density 0.054%

references to supernatural entities or themes

No Comments

No Known Activations