INDEX

Explanations

quotations indicating someone speaking or saying something

oai_token-act-pair · gpt-3.5-turbo

phrases indicating attribution or citation within scientific or academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

cffffcc

-0.88

anything

-0.86

à¼

-0.78

Offline

-0.77

usting

-0.77

ardless

-0.77

BRE

-0.76

ãĤ¦

-0.73

verage

-0.71

milo

-0.71

POSITIVE LOGITS

 researcher

1.23

 study

1.19

 Professor

1.18

Dr

1.13

 researchers

1.12

 biologist

1.10

 Prof

1.10

 lead

1.07

 Canaver

1.06

 Liang

1.05

Activations Density 0.116%

quotations indicating someone speaking or saying something

phrases indicating attribution or citation within scientific or academic contexts

No Comments

No Known Activations