INDEX

Explanations

words related to ears

oai_token-act-pair · gpt-3.5-turbo

references to hearing or ears

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ERO

-0.80

enance

-0.76

ABE

-0.72

 Leap

-0.71

 Vide

-0.71

VK

-0.68

Ide

-0.67

 Courier

-0.63

EEK

-0.62

antine

-0.62

POSITIVE LOGITS

ldom

1.24

phones

1.17

rings

1.11

 lobe

1.06

ear

1.02

phone

0.99

marked

0.99

wig

0.99

 canal

0.97

piece

0.95

Activations Density 0.017%

words related to ears

references to hearing or ears

No Comments

No Known Activations