INDEX

Explanations

descriptions of visual elements or illustrations in text

oai_token-act-pair · gpt-3.5-turbo

sentences containing visual descriptions or elements related to diagrams and images

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

 boycot

-0.84

 counselors

-0.83

 resusc

-0.80

 doctrines

-0.79

 ethics

-0.77

 concess

-0.77

 administr

-0.74

 taboo

-0.73

 reincarn

-0.73

 antidote

-0.73

POSITIVE LOGITS

 Notice

1.40

 Thumbnails

1.34

Notice

1.34

Figure

1.27

 Images

1.13

Credit

1.09

Images

1.09

Screenshot

1.08

image

1.07

Click

1.06

Activations Density 0.552%

descriptions of visual elements or illustrations in text

sentences containing visual descriptions or elements related to diagrams and images

No Comments

No Known Activations