INDEX

Explanations

terminology related to the nursing profession

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

 traveling

-1.49

 narrowing

-1.48

 wasting

-1.47

 saturated

-1.40

Ð½Ð°Ñĩ

-1.39

 lonely

-1.39

(>

-1.38

 travelling

-1.33

unden

-1.32

 unfavorable

-1.32

POSITIVE LOGITS

maid

2.11

hurst

2.02

nai

1.57

ti

1.56

ĩ

1.55

 assistant

1.55

¡

1.53

ctomy

1.50

entes

1.50

leneck

1.49

Activations Density 0.106%

terminology related to the nursing profession

No Comments

No Known Activations