INDEX

Explanations

mentions of a strong or notable presence

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "presence."

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

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

imb

-0.87

cipled

-0.76

bard

-0.74

mie

-0.72

ousse

-0.72

neys

-0.70

mort

-0.68

DIT

-0.68

jab

-0.68

romy

-0.68

POSITIVE LOGITS

 presence

0.98

enance

0.91

uated

0.82

 Presence

0.82

quo

0.73

iveness

0.68

uate

0.67

 unseen

0.67

 thereof

0.63

 abroad

0.62

Activations Density 0.028%

mentions of a strong or notable presence

references to the concept of "presence."

No Comments

No Known Activations