INDEX

Explanations

terminology related to driving

oai_token-act-pair · gpt-3.5-turbo

references to driving, specifically physical movement related to cars and vehicles

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

yip

-0.81

mint

-0.81

ept

-0.81

Ö¼

-0.80

iatus

-0.79

nces

-0.77

ipher

-0.76

ertain

-0.73

jri

-0.71

»Ĵ

-0.70

POSITIVE LOGITS

 wedge

1.25

err

0.78

 toward

0.73

 Zamb

0.72

 towards

0.72

 insane

0.71

 reck

0.68

 execution

0.68

 miles

0.68

 downhill

0.66

Activations Density 0.173%

terminology related to driving

references to driving, specifically physical movement related to cars and vehicles

No Comments

No Known Activations