INDEX

Explanations

words related to specific identities or classifications

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

noreply

-1.59

 heartbeat

-1.49

saf

-1.42

roit

-1.36

 Proced

-1.27

 probable

-1.25

 Fourth

-1.24

},\\

-1.23

amac

-1.22

 nearby

-1.22

POSITIVE LOGITS

 talks

1.71

uler

1.61

 negotiations

1.54

 discussions

1.49

ondo

1.49

 apart

1.43

inking

1.43

anian

1.42

gard

1.39

uled

1.38

Activations Density 0.538%

words related to specific identities or classifications

No Comments

No Known Activations