INDEX

Explanations

mentions of glioma or related terms in a medical context

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

noreply

-1.72

mas

-1.56

plasia

-1.54

itch

-1.46

nod

-1.46

hip

-1.44

ization

-1.39

ipt

-1.38

substack

-1.35

 sought

-1.35

POSITIVE LOGITS

ĻĤ

2.40

ģ

2.31

·

2.16

ª

2.15

·¸

2.09

Ĩ

2.06

¾

2.05

ĨĴ

2.00

ļ

2.00

į

1.96

Activations Density 0.103%

mentions of glioma or related terms in a medical context

No Comments

No Known Activations