INDEX

Explanations

letters or symbols that indicate some sort of emphasis or special character in text

oai_token-act-pair · gpt-3.5-turbo

peculiar or non-standard characters in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Pony

-0.79

 Crus

-0.74

 Seym

-0.70

 trainers

-0.70

*/(

-0.70

 Vaugh

-0.68

 therap

-0.66

ukong

-0.65

 skelet

-0.65

 emot

-0.65

POSITIVE LOGITS

ï¸ı

1.41

Â¯

0.95

nai

0.90

Ã±a

0.90

âĢ¢âĢ¢âĢ¢âĢ¢

0.89

uthor

0.88

ï¸

0.88

Ã±

0.88

Â£

0.86

Â¢

0.84

Activations Density 0.109%

letters or symbols that indicate some sort of emphasis or special character in text

peculiar or non-standard characters in the text

No Comments

No Known Activations