INDEX

Explanations

references to military or governmental organizations and related activities

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

"}](#

-1.82

 lives

-1.59

illin

-1.53

ental

-1.52

indi

-1.47

 called

-1.46

 myself

-1.46

 ages

-1.41

msgstr

-1.41

googleapis

-1.39

POSITIVE LOGITS

»¿

2.86

2.66

<|outofrange|>

2.66

↵Č

2.66

↵

2.66

↵

2.66

↵

2.66

č↵

2.66

Activations Density 0.556%

references to military or governmental organizations and related activities

No Comments

No Known Activations