INDEX

Explanations

words related to increase, improvement, and decrease

oai_token-act-pair · gpt-3.5-turbo

phrases indicating an increase or improvement in something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

mad

-0.77

bent

-0.67

çĦ

-0.66

ilo

-0.64

ç«

-0.60

thing

-0.60

oof

-0.60

Ñģ

-0.60

swe

-0.60

DragonMagazine

-0.59

POSITIVE LOGITS

 productivity

1.03

 efficiency

1.00

 morale

0.98

 visibility

0.95

 longevity

0.93

 enormously

0.92

 circulation

0.91

 exponentially

0.91

 perceptions

0.91

 reliability

0.89

Activations Density 0.189%

words related to increase, improvement, and decrease

phrases indicating an increase or improvement in something

No Comments

No Known Activations