INDEX

Explanations

descriptions of inventions and their applications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/2-res-sm

Prompts (Dashboard)

32,768 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

torch.float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

standard

Context Size

128

Dataset

EleutherAI/the_pile_deduplicated

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

į

-3.81

ĭ

-3.74

Ļª

-3.46

»¿

-3.42

Ĵ

-3.37

Ħ

-3.31

Ģ

-3.16

ĳ

-3.08

Ĩ

-3.08

č↵č↵

-3.07

POSITIVE LOGITS

 favorably

1.62

acious

1.59

 accordingly

1.49

 merely

1.45

amente

1.45

 stay

1.45

 hereto

1.42

 itself

1.41

pecially

1.41

 states

1.40

Activations Density 0.063%

descriptions of inventions and their applications

No Comments

No Known Activations