INDEX

Explanations

references to the country "China"

oai_token-act-pair · gpt-3.5-turbo

mentions of China

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RH

-0.74

rawdownloadcloneembedreportprint

-0.73

âĢ¢âĢ¢âĢ¢âĢ¢

-0.72

RTX

-0.69

iotic

-0.69

 Bram

-0.68

docker

-0.68

 Seym

-0.68

schild

-0.67

mares

-0.65

POSITIVE LOGITS

 Jinping

1.12

 Yuan

0.93

 Unic

0.89

 yuan

0.84

 Jing

0.84

 nationals

0.83

China

0.82

jing

0.80

Zhu

0.79

 China

0.79

Activations Density 0.030%

references to the country "China"

mentions of China

No Comments

No Known Activations