INDEX

Explanations

the word "where" indicating locations or contexts

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

¬

-3.17

ŀ

-3.01

↵

-2.78

↵

-2.78

<|outofrange|>

-2.78

↵↵

-2.78

↵

-2.78

↵↵

-2.78

POSITIVE LOGITS

mails

1.59

birds

1.54

 area

1.52

 Caption

1.51

 variables

1.51

isters

1.49

amps

1.49

ocks

1.48

ites

1.43

panic

1.43

Activations Density 0.007%

the word "where" indicating locations or contexts

No Comments

No Known Activations