INDEX

Explanations

media captions and related textual descriptions

oai_token-act-pair · gpt-3.5-turbo

captions in media-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĪĴ

-0.79

walker

-0.72

Magikarp

-0.72

nesia

-0.70

vals

-0.69

Ö¼

-0.66

 bowling

-0.64

urat

-0.64

atto

-0.64

»Ĵ

-0.64

POSITIVE LOGITS

 WATCH

0.83

acters

0.77

 Theresa

0.72

 Corbyn

0.69

ITV

0.69

BBC

0.69

 Natasha

0.67

 Prof

0.67

 Survive

0.66

=-=-=-=-=-=-=-=-

0.66

Activations Density 0.004%

media captions and related textual descriptions

captions in media-related content

No Comments

No Known Activations