INDEX

Explanations

instances of people lying down or being in a prone position

oai_token-act-pair · gpt-3.5-turbo

instances of people lying or positioned in various ways

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

 Flavoring

-0.82

ãĥķãĤ©

-0.80

allo

-0.78

ãĥīãĥ©ãĤ´ãĥ³

-0.75

ãĥĪ

-0.73

sylv

-0.73

ãĥ©ãĥ³

-0.72

ocy

-0.71

ormons

-0.71

 Cosponsors

-0.70

POSITIVE LOGITS

 slumped

1.11

 beside

1.11

 kneeling

1.00

 crou

0.99

 seiz

0.99

 comfortably

0.96

 asleep

0.95

 unconscious

0.94

 peacefully

0.93

 clutching

0.92

Activations Density 0.145%

instances of people lying down or being in a prone position

instances of people lying or positioned in various ways

No Comments

No Known Activations