INDEX

Explanations

references to countries, especially China and its international relations

oai_token-act-pair · gpt-3.5-turbo

references to China and its geopolitical relationships and actions

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

etime

-0.73

 "$:/

-0.70

estyles

-0.67

dx

-0.67

tml

-0.66

bleacher

-0.66

ciating

-0.66

td

-0.65

soDeliveryDate

-0.65

apple

-0.65

POSITIVE LOGITS

's

0.94

ÃŃs

0.87

 ally

0.86

 officials

0.81

 participates

0.79

 Arabia

0.78

 considers

0.75

 consulate

0.75

gged

0.75

 authorities

0.75

Activations Density 0.161%

references to countries, especially China and its international relations

references to China and its geopolitical relationships and actions

No Comments

No Known Activations