INDEX

Explanations

mentions of specific names and terms, likely related to a particular topic or theme

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

matically

-1.03

pec

-0.84

¶æ

-0.83

ments

-0.81

ment

-0.79

mercial

-0.78

ming

-0.76

asing

-0.76

pee

-0.75

gdala

-0.73

POSITIVE LOGITS

 Diesel

0.70

 Bagg

0.66

edit

0.63

ersen

0.63

icz

0.62

 laundry

0.61

 Lakes

0.61

DragonMagazine

0.61

 Meier

0.60

amily

0.59

Activations Density 0.117%

mentions of specific names and terms, likely related to a particular topic or theme

No Comments

No Known Activations