INDEX

Explanations

mentions of employees within a professional or work-related context

oai_token-act-pair · gpt-3.5-turbo

the term "staffer" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

powers

-0.67

ĵĺ

-0.65

ushima

-0.64

ued

-0.64

asca

-0.64

ãĥ¼ãĥ³

-0.64

frog

-0.63

¥µ

-0.63

Companies

-0.63

 Sabha

-0.62

POSITIVE LOGITS

irtual

0.82

 staffer

0.78

 reception

0.78

 Emails

0.76

 staffers

0.74

email

0.73

hips

0.72

olor

0.72

bnb

0.68

 interns

0.68

Activations Density 0.021%

mentions of employees within a professional or work-related context

the term "staffer" and its variations

No Comments

No Known Activations