INDEX

Explanations

numerical values related to health metrics and measurements

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

arts

-1.57

rek

-1.44

saw

-1.44

vÃ©

-1.41

 Expect

-1.40

athed

-1.39

ubs

-1.38

 surely

-1.37

aped

-1.35

committee

-1.33

POSITIVE LOGITS

¶

1.65

¦

1.60

µ

1.53

®

1.49

Į

1.49

FU

1.46

Ļª

1.44

ersion

1.43

ings

1.39

.“

1.38

Activations Density 0.037%

numerical values related to health metrics and measurements

No Comments

No Known Activations