INDEX

Explanations

phrases indicating effort or intentionality

oai_token-act-pair · gpt-3.5-turbo

expressions indicating effort or the act of making an effort

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

soDeliveryDate

-0.85

 Lots

-0.66

ellation

-0.66

lot

-0.65

anooga

-0.64

 Used

-0.63

vice

-0.62

fair

-0.62

ERA

-0.62

going

-0.61

POSITIVE LOGITS

 remind

1.03

 acknowledge

0.96

 indulge

0.96

 breathe

0.94

 introduce

0.94

 declare

0.94

 endorse

0.92

 defy

0.92

 criticize

0.92

 speak

0.91

Activations Density 0.142%

phrases indicating effort or intentionality

expressions indicating effort or the act of making an effort

No Comments

No Known Activations