INDEX

Explanations

the presence of a specific term or keyword related to 'ag' or 'agencies'

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

Ĥ¬

-2.12

ĸ´

-2.05

Ĥ

-2.00

´

-1.97

¨

-1.92

ĭ

-1.87

ħ

-1.85

?)

-1.83

?).

-1.81

ı

-1.79

POSITIVE LOGITS

gregation

1.70

gered

1.66

doll

1.54

RET

1.50

bucks

1.45

rangian

1.45

 submissions

1.44

gers

1.44

 exhausted

1.42

ostic

1.39

Activations Density 0.021%

the presence of a specific term or keyword related to 'ag' or 'agencies'

No Comments

No Known Activations