INDEX

Explanations

credits and sources mentioned in an article or document

oai_token-act-pair · gpt-3.5-turbo

references to images and their sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

iqueness

-0.72

entimes

-0.67

 poison

-0.66

answered

-0.66

 Audit

-0.65

adj

-0.62

 loyalty

-0.62

terness

-0.61

-----------

-0.61

Â¶

-0.61

POSITIVE LOGITS

 Shutterstock

1.70

 Flickr

1.55

photos

1.49

utterstock

1.41

 Wikimedia

1.32

Flickr

1.15

images

1.15

 Courtesy

1.12

img

1.09

Pix

1.07

Activations Density 0.155%

credits and sources mentioned in an article or document

references to images and their sources

No Comments

No Known Activations