INDEX

Explanations

words or phrases related to someone's presence or involvement in an event or situation

oai_token-act-pair · gpt-3.5-turbo

mentions of public appearances or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

rals

-0.85

cedented

-0.80

imb

-0.77

EStreamFrame

-0.77

cise

-0.72

ollow

-0.69

ricular

-0.68

yth

-0.66

regate

-0.66

emetery

-0.66

POSITIVE LOGITS

 appearances

1.07

 appearance

1.04

 Appearance

0.86

lihood

0.85

Magikarp

0.76

DragonMagazine

0.75

çİĭ

0.70

å·

0.70

 Chimera

0.69

 flaws

0.67

Activations Density 0.017%

words or phrases related to someone's presence or involvement in an event or situation

mentions of public appearances or events

No Comments

No Known Activations