INDEX

Explanations

phrases related to collaboration and unity

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

DragonMagazine

-0.73

OGR

-0.72

wine

-0.71

 Illustrated

-0.71

LOG

-0.68

Gi

-0.66

IDE

-0.66

ynes

-0.65

IAL

-0.65

soever

-0.63

POSITIVE LOGITS

 asserting

1.29

 rejecting

1.28

 achieving

1.27

 recognizing

1.26

 recommending

1.23

 locating

1.22

 adopting

1.22

 finding

1.22

 resolving

1.21

 declaring

1.20

Activations Density 0.120%

phrases related to collaboration and unity

occurrences of the word "in"

No Comments

No Known Activations