INDEX

Explanations

questions posed around a variety of topics

oai_token-act-pair · gpt-3.5-turbo

the word "whether" and associated questions or considerations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

aging

-0.83

viron

-0.73

izing

-0.71

ija

-0.71

ages

-0.71

thal

-0.70

Eye

-0.69

ursed

-0.67

bing

-0.67

ID

-0.66

POSITIVE LOGITS

soever

1.35

yip

0.88

whether

0.80

 whether

0.80

ornia

0.72

aminer

0.70

 nodd

0.69

 warr

0.67

 reluct

0.67

terday

0.65

Activations Density 0.032%

questions posed around a variety of topics

the word "whether" and associated questions or considerations

No Comments

No Known Activations