INDEX

Explanations

references to specific brands or products

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 unsuccessful

-1.57

'),

-1.50

 site

-1.50

');

-1.47

 successful

-1.46

 neighbouring

-1.43

 fruitful

-1.38

 offices

-1.32

abouts

-1.32

 vain

-1.31

POSITIVE LOGITS

¥

4.71

¿

4.59

ģ

4.41

ĩ

4.37

Ļª

4.36

Ń

4.33

²

4.17

£

4.16

·¸

4.09

°

3.97

Activations Density 0.932%

references to specific brands or products

No Comments

No Known Activations