INDEX

Explanations

the occurrence of the word "two."

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

 NOTICE

-1.64

ŀ

-1.51

 reasons

-1.50

ARI

-1.38

 BASIS

-1.38

 audible

-1.36

 advertisements

-1.36

ocyanate

-1.34

Ã±os

-1.33

aria

-1.32

POSITIVE LOGITS

ston

1.63

gets

1.60

osity

1.55

Gs

1.55

genstein

1.54

Std

1.51

libs

1.46

geometric

1.45

weg

1.45

friends

1.44

Activations Density 0.065%

the occurrence of the word "two."

No Comments

No Known Activations