INDEX

Explanations

mentions of professions or professional activities

oai_token-act-pair · gpt-3.5-turbo

terms related to professionalism in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Eggs

-0.72

wic

-0.72

 wherein

-0.70

eny

-0.70

Spawn

-0.69

heit

-0.69

loads

-0.68

via

-0.67

blocks

-0.66

pox

-0.65

POSITIVE LOGITS

 professional

3.46

Professional

2.57

professional

2.57

 Professional

2.47

 professionally

2.29

 professionals

2.12

 professionalism

1.83

 amateur

1.70

 Profession

1.50

 collegiate

1.48

Activations Density 0.017%

mentions of professions or professional activities

terms related to professionalism in various contexts

No Comments

No Known Activations