INDEX

Explanations

references to superhero comics and movies

oai_token-act-pair · gpt-3.5-turbo

references to the interconnectedness of comic book movie universes and their characters

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

 Eston

-1.03

 Allaah

-0.90

 Estonia

-0.89

Äį

-0.88

ë

-0.87

Ã¥

-0.87

 fixme

-0.84

ë

-0.84

ersen

-0.84

 Erit

-0.83

POSITIVE LOGITS

 Superman

1.70

 Batman

1.64

 superhero

1.54

 superheroes

1.53

 Luthor

1.51

Batman

1.51

 Deadpool

1.49

 Marvel

1.46

 Gotham

1.44

 Krypt

1.43

Activations Density 0.702%

references to superhero comics and movies

references to the interconnectedness of comic book movie universes and their characters

No Comments

No Known Activations