INDEX

Explanations

genres of literary works, including fantasy, science fiction, horror, surreal, weird, and more

oai_token-act-pair · gpt-3.5-turbo

references to various music and literary genres

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

osponsors

-0.90

ulia

-0.89

onds

-0.82

orsi

-0.76

payers

-0.75

poons

-0.73

ptoms

-0.73

months

-0.73

undred

-0.72

installed

-0.72

POSITIVE LOGITS

sci

1.36

 futuristic

1.33

 thriller

1.26

 Gothic

1.22

 dystopian

1.22

 gritty

1.21

 techno

1.19

 comedy

1.17

 punk

1.17

 comedic

1.16

Activations Density 0.511%

genres of literary works, including fantasy, science fiction, horror, surreal, weird, and more

references to various music and literary genres

No Comments

No Known Activations