INDEX

Explanations

mentions of retail locations and activities

oai_token-act-pair · gpt-3.5-turbo

the word "retail" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

asso

-0.78

zu

-0.72

Kaf

-0.71

anti

-0.69

CHA

-0.68

cha

-0.67

 Joined

-0.67

vati

-0.66

chu

-0.66

åŃ

-0.66

POSITIVE LOGITS

 retail

3.60

 Retail

2.70

 retailers

2.30

 retailer

2.19

 wholesale

1.56

 manufacturing

1.53

 storefront

1.52

 shops

1.48

 stores

1.43

 Walmart

1.41

Activations Density 0.014%

mentions of retail locations and activities

the word "retail" and its variations

No Comments

No Known Activations