INDEX

Explanations

phrases related to redirects for different topics or uses

oai_token-act-pair · gpt-3.5-turbo

references to specific films and articles

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

 mosqu

-0.62

 transmitting

-0.58

fman

-0.58

 neighb

-0.57

 overs

-0.57

 UNCLASSIFIED

-0.56

 PLUS

-0.55

 ðŁĻĤ

-0.55

ertodd

-0.55

 lobb

-0.55

POSITIVE LOGITS

Appearances

0.73

wiki

0.72

pedia

0.71

 Manga

0.70

loc

0.70

 wiki

0.70

 enchantment

0.68

 trope

0.64

ãĤ´

0.64

channelAvailability

0.63

Activations Density 0.112%

phrases related to redirects for different topics or uses

references to specific films and articles

No Comments

No Known Activations