INDEX

Explanations

instances related to driving, vehicles, and car accidents

oai_token-act-pair · gpt-3.5-turbo

mentions of drivers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

iversal

-0.80

aeper

-0.79

yss

-0.78

achu

-0.77

 Flavoring

-0.76

ertain

-0.73

ropolitan

-0.72

reme

-0.72

pta

-0.72

orkshire

-0.71

POSITIVE LOGITS

 drivers

0.94

 driver

0.93

 pige

0.90

driving

0.84

driver

0.83

less

0.83

 bees

0.80

 driving

0.78

 Drivers

0.78

wings

0.77

Activations Density 0.016%

instances related to driving, vehicles, and car accidents

mentions of drivers in various contexts

No Comments

No Known Activations