INDEX

Explanations

phrases related to the Chinese President Xi Jinping

oai_token-act-pair · gpt-3.5-turbo

mentions of the Chinese President, Xi Jinping

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

rawdownloadcloneembedreportprint

-0.79

 captcha

-0.77

LOAD

-0.76

 SPORTS

-0.76

fully

-0.74

lighting

-0.73

 Grail

-0.71

landish

-0.70

Ö¼

-0.69

ãĥĨ

-0.68

POSITIVE LOGITS

 Jinping

1.98

ongyang

1.00

Xi

0.90

ijing

0.87

 Jing

0.86

adra

0.86

illus

0.85

esta

0.85

uria

0.83

Xi

0.81

Activations Density 0.023%

phrases related to the Chinese President Xi Jinping

mentions of the Chinese President, Xi Jinping

No Comments

No Known Activations