INDEX

Explanations

phrases emphasizing exclusivity or singularity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ļ

-1.83

ĸ

-1.73

 angles

-1.64

Ļ

-1.59

 generations

-1.57

 directions

-1.54

¹

-1.49

 steps

-1.48

ories

-1.48

rations

-1.46

POSITIVE LOGITS

forge

1.80

upon

1.61

jam

1.60

CTX

1.59

yon

1.58

xiv

1.57

 safely

1.56

GRP

1.56

quote

1.56

MTP

1.55

Activations Density 0.312%

phrases emphasizing exclusivity or singularity

No Comments

No Known Activations