INDEX

Explanations

patterns of formatting in textual data, such as decoration or emphasis markers

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

omer

-1.68

 bond

-1.67

ubot

-1.64

pite

-1.61

irc

-1.60

rypt

-1.58

 undergo

-1.57

 comply

-1.55

ird

-1.49

ically

-1.49

POSITIVE LOGITS

~~~

1.77

 fiction

1.63

rooms

1.63

 Someone

1.50

 hints

1.47

 bathrooms

1.39

stylesheet

1.37

 generality

1.36

dates

1.36

room

1.34

Activations Density 0.010%

patterns of formatting in textual data, such as decoration or emphasis markers

No Comments

No Known Activations