INDEX

Explanations

keywords related to advertisements or ads

oai_token-act-pair · gpt-3.5-turbo

references to advertisements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ĨĴ

-0.82

 Caribbean

-0.72

bred

-0.72

 IPCC

-0.72

 Dice

-0.71

lihood

-0.71

 Cyprus

-0.70

Jr

-0.70

 Circle

-0.69

 Patriarch

-0.66

POSITIVE LOGITS

vertising

1.13

ads

1.03

 advertising

0.92

elaide

0.92

vertisement

0.91

verts

0.90

strip

0.89

 billboards

0.88

 nause

0.86

vertisements

0.85

Activations Density 0.016%

keywords related to advertisements or ads

references to advertisements

No Known Activations