INDEX

Explanations

occurrences of the word "annuity."

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

Americans

-1.60

 rapid

-1.60

FIG

-1.48

 direct

-1.47

ATER

-1.46

))?

-1.46

 normal

-1.40

 orderly

-1.40

coat

-1.40

 Federal

-1.39

POSITIVE LOGITS

pieces

1.72

ue

1.61

iom

1.56

rams

1.54

erals

1.54

arie

1.53

uelle

1.49

uli

1.49

lis

1.46

ilus

1.46

Activations Density 0.008%

occurrences of the word "annuity."

No Comments

No Known Activations