INDEX

Explanations

references to different product or service offerings

oai_token-act-pair · gpt-3.5-turbo

the term "offerings" in various contexts related to products or services

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

Negative Logits

cop

-0.67

author

-0.65

wash

-0.63

 Aerospace

-0.62

 Adinida

-0.62

 edit

-0.61

sf

-0.60

 Mayo

-0.60

abol

-0.60

ca

-0.60

POSITIVE LOGITS

 offerings

1.51

plings

0.95

 offering

0.89

ĸļ

0.84

uggest

0.83

jriwal

0.83

 discounts

0.82

pta

0.81

ngth

0.81

xual

0.81

Activations Density 0.007%

references to different product or service offerings

the term "offerings" in various contexts related to products or services

No Known Activations