INDEX

Explanations

numerical values and their significance in context

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

 mean

-1.48

 difference

-1.47

rely

-1.45

 capitalism

-1.45

arians

-1.41

 doubt

-1.39

 mere

-1.39

 theory

-1.37

"?"

-1.36

opol

-1.35

POSITIVE LOGITS

¶

2.81

¿½

2.76

¥

2.70

ģ

2.65

Ĥ

2.59

®

2.55

ĸ

2.52

º

2.49

Ĭ

2.48

¬

2.43

Activations Density 0.172%

numerical values and their significance in context

No Comments

No Known Activations