INDEX

Explanations

phrases related to political figures and events

oai_token-act-pair · gpt-3.5-turbo

references to notable individuals or entities

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

BuyableInstoreAndOnline

-0.83

 ponds

-0.71

 Monroe

-0.69

 Compass

-0.63

 Wonderland

-0.63

 Bonds

-0.63

aston

-0.61

 Chains

-0.60

 Arri

-0.60

 seiz

-0.60

POSITIVE LOGITS

cipled

1.06

ciples

1.03

itte

0.82

bably

0.82

xus

0.78

formance

0.73

aceutical

0.72

andom

0.72

eed

0.71

issance

0.71

Activations Density 0.074%

phrases related to political figures and events

references to notable individuals or entities

No Comments

No Known Activations