INDEX

Explanations

phrases or sentences related to opinions or viewpoints

oai_token-act-pair · gpt-3.5-turbo

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

Not in Any Lists

No Comments

Negative Logits

 Brist

-0.81

anwhile

-0.79

Osw

-0.79

RAD

-0.76

 Cosmetic

-0.75

 airs

-0.74

 horizont

-0.74

ifications

-0.73

 Palest

-0.72

Downloadha

-0.72

POSITIVE LOGITS

¬

1.47

Ļ

1.22

¥

1.14

¡

1.14

ı

1.11

£

1.10

Ķ

1.08

Ń

1.04

Ĵ

1.03

ª

1.03

Activations Density 0.323%

phrases or sentences related to opinions or viewpoints

No Comments

No Known Activations