INDEX

Explanations

the word "all" followed by another word or phrase

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing totality or inclusivity

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

rouse

-0.71

anova

-0.69

inates

-0.68

agin

-0.68

isol

-0.66

illus

-0.64

ettel

-0.64

izo

-0.64

FAR

-0.63

KE

-0.63

POSITIVE LOGITS

int

1.06

 eternity

1.05

 purposes

1.03

 practical

1.01

 sake

1.00

 foreseeable

0.85

 sorts

0.83

ocating

0.81

 appearances

0.78

usions

0.77

Activations Density 0.033%

the word "all" followed by another word or phrase

phrases emphasizing totality or inclusivity

No Comments

No Known Activations