INDEX

Explanations

quotation marks, indicating the presence of dialogue or quoted speech

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

ization

-1.66

emann

-1.65

 approach

-1.61

 instrument

-1.61

 apparatus

-1.59

ensation

-1.57

iative

-1.56

 Approach

-1.54

izing

-1.52

ocene

-1.51

POSITIVE LOGITS

 yourselves

2.40

 yourself

2.14

 ourselves

1.84

 myself

1.72

 harmless

1.50

EEEE

1.38

 Magistrate

1.37

safe

1.34

cin

1.33

 presidential

1.33

Activations Density 0.279%

quotation marks, indicating the presence of dialogue or quoted speech

No Comments

No Known Activations