INDEX

Explanations

photos or images

oai_token-act-pair · gpt-3.5-turbo

mentions of photographs or photos

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ensable

-0.84

merce

-0.76

Mand

-0.75

ressive

-0.74

aples

-0.73

unin

-0.72

inence

-0.71

auri

-0.70

endez

-0.70

resses

-0.70

POSITIVE LOGITS

photos

1.06

journal

1.05

 illustration

0.99

 Photographer

0.93

 photo

0.91

>>>>>>>>

0.90

 Phot

0.85

 shoots

0.85

 photographed

0.84

photo

0.83

Activations Density 0.029%

photos or images

mentions of photographs or photos

No Comments

No Known Activations