INDEX

Explanations

words related to publications or releases of books, movies, or series

oai_token-act-pair · gpt-3.5-turbo

the presence of end-of-text markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

advant

-0.80

hap

-0.73

ealous

-0.71

ghazi

-0.70

chuk

-0.69

odan

-0.66

ague

-0.63

 Administ

-0.63

ertodd

-0.62

vantage

-0.62

POSITIVE LOGITS

 anthology

1.01

 premie

0.98

 premiere

0.97

 paperback

0.90

isodes

0.89

 theaters

0.84

 installment

0.84

 debut

0.81

 release

0.81

 collaborations

0.81

Activations Density 0.857%

words related to publications or releases of books, movies, or series

the presence of end-of-text markers

No Comments

No Known Activations