INDEX

Explanations

terms related to the software Adobe Photoshop

oai_token-act-pair · gpt-3.5-turbo

references to Adobe software and its features

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

owship

-0.91

pole

-0.82

idential

-0.81

ership

-0.78

auri

-0.74

lves

-0.72

onso

-0.72

ths

-0.71

undai

-0.70

idem

-0.69

POSITIVE LOGITS

 Photoshop

1.02

oshop

0.95

RGB

0.84

 Â®

0.84

ABE

0.83

 canvas

0.80

CS

0.77

 CLSID

0.75

 workflow

0.75

 Elements

0.73

Activations Density 0.039%

terms related to the software Adobe Photoshop

references to Adobe software and its features

No Comments

No Known Activations