INDEX

Explanations

terms related to emissions and luminescence in scientific contexts

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

izumab

-1.79

lament

-1.67

asta

-1.58

zyk

-1.56

uttered

-1.55

hest

-1.54

ÃŃses

-1.50

asted

-1.50

anus

-1.50

irmat

-1.48

POSITIVE LOGITS

 capability

1.65

 means

1.65

 capacities

1.64

encies

1.63

 properties

1.58

 capabilities

1.58

 government

1.57

government

1.55

 spectrum

1.52

 films

1.50

Activations Density 0.057%

terms related to emissions and luminescence in scientific contexts

No Comments

No Known Activations