INDEX

Explanations

references to the pronoun "she."

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

heres

-1.78

 others

-1.64

itates

-1.60

imony

-1.59

ursuant

-1.59

://

-1.58

chaft

-1.57

ethe

-1.55

 congress

-1.46

 aliens

-1.45

POSITIVE LOGITS

pherd

2.62

ģ

2.10

¿

2.04

ffield

2.00

pher

1.88

Ļ

1.75

dule

1.74

Ã±o

1.71

ega

1.67

à±į

1.65

Activations Density 0.100%

references to the pronoun "she."

No Comments

No Known Activations