INDEX

Explanations

expressions of approval and disapproval

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

ical

-1.67

rely

-1.66

andez

-1.61

otle

-1.55

uality

-1.52

orget

-1.50

forth

-1.49

ALSE

-1.48

ANCE

-1.47

older

-1.44

POSITIVE LOGITS

 granted

1.59

 awarded

1.51

 shutter

1.50

 loro

1.48

 reproduce

1.45

 feat

1.43

 topp

1.43

win

1.42

=”

1.41

fileID

1.40

Activations Density 0.021%

expressions of approval and disapproval

No Comments

No Known Activations