INDEX

Explanations

references to geographical locations and institutions

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

 catalogue

-1.64

cknowled

-1.63

º

-1.61

Ļª

-1.60

Ĵ

-1.60

ª

-1.53

-1.50

<|outofrange|>

-1.50

↵

-1.50

POSITIVE LOGITS

,'"

1.73

.'"

1.73

]'

1.72

"}](#

1.49

experienced

1.48

;;

1.46

];

1.43

,'

1.43

 necessarily

1.40

}(

1.40

Activations Density 4.655%

references to geographical locations and institutions

No Comments

No Known Activations