INDEX

Explanations

terms related to weight, particularly in the context of weight management and health

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.0.hook_mlp_out

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

thood

-1.86

uginosa

-1.65

 mind

-1.56

 Majesty

-1.55

 Spacewatch

-1.55

áĢº

-1.52

chell

-1.50

ureus

-1.50

patient

-1.48

opes

-1.48

POSITIVE LOGITS

ĻĤ

1.94

loader

1.78

ģ

1.68

ily

1.65

wise

1.63

achusetts

1.60

 spectrometer

1.49

tag

1.49

 spectrom

1.48

ier

1.46

Activations Density 0.021%

terms related to weight, particularly in the context of weight management and health

No Comments

No Known Activations