INDEX

Explanations

words related to comic books or comic book characters

oai_token-act-pair · gpt-3.5-turbo

mentions of comic books and their related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

beam

-0.81

ntil

-0.79

tenance

-0.74

ysis

-0.72

gain

-0.70

holm

-0.70

aton

-0.68

come

-0.67

ŃĶ

-0.64

ware

-0.64

POSITIVE LOGITS

 Comics

0.95

 Presents

0.81

 comics

0.80

 superheroes

0.80

 originals

0.77

andise

0.76

linger

0.76

lisher

0.76

strip

0.75

 adaptations

0.75

Activations Density 0.023%

words related to comic books or comic book characters

mentions of comic books and their related terminology

No Comments

No Known Activations