INDEX

Explanations

numerical ratings or scores associated with various entities or evaluations

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

"?"

-1.75

river

-1.62

CDATA

-1.51

usterity

-1.50

ACE

-1.49

cha

-1.47

ker

-1.47

 least

-1.44

 question

-1.43

hentication

-1.43

POSITIVE LOGITS

®

3.43

µ

3.22

°

3.02

¶

2.94

¾

2.86

³

2.73

¥

2.66

Ń

2.63

ª

2.59

ģ

2.54

Activations Density 0.012%

numerical ratings or scores associated with various entities or evaluations

No Comments

No Known Activations