INDEX

Explanations

instances of the word "doing."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apine

-1.94

noreply

-1.82

ieu

-1.55

she

-1.53

odia

-1.47

osal

-1.44

 saying

-1.40

rea

-1.38

Ã©ment

-1.37

appa

-1.36

POSITIVE LOGITS

xy

1.69

 exercises

1.67

°

1.63

 deficits

1.63

 deficit

1.60

gs

1.58

gered

1.51

Ļ

1.50

ctors

1.48

º

1.47

Activations Density 0.152%

instances of the word "doing."

No Comments

No Known Activations