INDEX

Explanations

social media hashtags or tagging indicators, such as "@" and hashtags

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or string representation 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 @ 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

 Silk

-0.72

 Whis

-0.71

 Vaugh

-0.69

Nam

-0.68

 Morg

-0.66

 Mayo

-0.65

 shroud

-0.65

 spinning

-0.65

Peb

-0.64

 Carbuncle

-0.64

POSITIVE LOGITS

º

1.15

¹

1.12

į

1.01

§

1.00

£

1.00

»

0.98

¬

0.97

®

0.95

¿

0.95

¡

0.95

Activations Density 0.116%

social media hashtags or tagging indicators, such as "@" and hashtags

instances of a specific character or string representation in the text

No Comments

No Known Activations