INDEX

Explanations

references to characters and elements from the Star Wars universe

oai_token-act-pair · gpt-3.5-turbo

references to characters from the Star Wars franchise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ãĥĥãĥĪ

-0.81

FUN

-0.79

Ö¼

-0.78

esville

-0.78

âķĲâķĲ

-0.78

geoning

-0.76

Ü

-0.74

IGF

-0.68

uments

-0.68

ãĥ¼ãĥĨ

-0.68

POSITIVE LOGITS

 Skywalker

1.41

 Vader

1.21

 Kenobi

1.14

 lightsaber

1.03

actic

0.94

 Leia

0.92

acca

0.91

 Rebels

0.91

Wan

0.89

 droid

0.87

Activations Density 0.038%

references to characters and elements from the Star Wars universe

references to characters from the Star Wars franchise

No Comments

No Known Activations