INDEX

Explanations

mentions of specific operating systems and software-related terms

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

quo

-1.84

 infertility

-1.76

 death

-1.53

icable

-1.47

 agenda

-1.46

 warranted

-1.42

 ambitious

-1.41

 career

-1.40

DESC

-1.32

 autoimmune

-1.29

POSITIVE LOGITS

ooth

1.68

]];

1.67

stic

1.61

Ń

1.58

¢

1.58

.]{}

1.57

inger

1.57

.]

1.51

cdn

1.51

assen

1.48

Activations Density 1.278%

mentions of specific operating systems and software-related terms

No Comments

No Known Activations