INDEX

Explanations

terms related to duration and possibly limitation in time

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

ene

-1.91

ledge

-1.61

ses

-1.60

ĥ½

-1.55

ward

-1.55

ifically

-1.53

elij

-1.52

ail

-1.52

 faces

-1.48

ribe

-1.45

POSITIVE LOGITS

"}](#

1.98

]'

1.62

]",

1.55

)',

1.52

'+

1.49

ontal

1.45

 Parenthood

1.44

)"

1.39

uto

1.36

?'

1.36

Activations Density 0.048%

terms related to duration and possibly limitation in time

No Comments

No Known Activations