INDEX

Explanations

keywords related to specific events or announcements

oai_token-act-pair · gpt-3.5-turbo

specific terms associated with various categories of information, including medical, musical, community-related, and more

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

igr

-0.73

Attempts

-0.65

Recomm

-0.65

SHIP

-0.64

votes

-0.63

Stud

-0.63

Impro

-0.62

ãĥį

-0.62

âĸ¬

-0.61

Temperature

-0.60

POSITIVE LOGITS

are

1.43

 aren

1.36

 abound

1.35

 were

1.30

 weren

1.27

ARE

1.17

pring

1.07

peed

1.03

were

1.03

mith

1.00

Activations Density 0.697%

keywords related to specific events or announcements

specific terms associated with various categories of information, including medical, musical, community-related, and more

No Known Activations