INDEX

Explanations

terminology related to inventions and patent information

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

New Auto-Interp

Configuration

ctigges/pythia-70m-deduped__res-sm_processed/1-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.1.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

 âĢķ

-1.70

 manually

-1.57

âĢħ

-1.52

âĢĬ

-1.52

 anymore

-1.51

 themselves

-1.48

 remotely

-1.39

```

-1.37

ginx

-1.35

à³

-1.34

POSITIVE LOGITS

Į

2.62

ĻĤ

2.60

ª

2.59

¿½

2.45

Ħ

2.30

ķ

2.28

Ļ

2.21

Ĥ

2.16

Ĭ

2.16

ħ

2.15

Activations Density 0.072%

terminology related to inventions and patent information

No Comments

No Known Activations