INDEX

Explanations

details about brand identity or branding practices

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sever

-1.49

 ownership

-1.39

amente

-1.35

anted

-1.33

 alike

-1.31

"-

-1.30

hee

-1.29

ÃĤ

-1.27

*"

-1.26

ystem

-1.26

POSITIVE LOGITS

Errno

1.46

ttes

1.42

 tonight

1.41

ings

1.37

 yours

1.34

 tomorrow

1.32

lights

1.31

orna

1.29

 pretext

1.28

ismiss

1.27

Activations Density 9.490%

details about brand identity or branding practices

No Comments

No Known Activations