INDEX

Explanations

references to locations or places in the text

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

 adults

-1.55

#{

-1.47

respectively

-1.46

 possible

-1.46

 cross

-1.43

?_

-1.42

 moderation

-1.42

 straight

-1.42

 independence

-1.39

?"

-1.38

POSITIVE LOGITS

holder

2.27

aho

1.98

bel

1.94

bum

1.92

vist

1.87

plates

1.86

veolar

1.83

pit

1.83

endor

1.80

ente

1.79

Activations Density 0.048%

references to locations or places in the text

No Comments

No Known Activations