INDEX

Explanations

phrases related to self-improvement and personal development

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ocaust

-0.76

 Chern

-0.75

 piracy

-0.73

 Murdoch

-0.73

Iraq

-0.70

atel

-0.70

 cartel

-0.67

 Amnesty

-0.66

 Auschwitz

-0.66

 munitions

-0.65

POSITIVE LOGITS

 mindfulness

1.03

 subconscious

0.94

 unconsciously

0.91

cknow

0.83

 Technique

0.82

 beginner

0.82

 dopamine

0.81

 habits

0.80

 therapist

0.80

xiety

0.80

Activations Density 1.533%

phrases related to self-improvement and personal development

No Comments

No Known Activations