INDEX

Explanations

phrases related to showcasing or demonstrating new products or technologies

oai_token-act-pair · gpt-3.5-turbo

mentions of new technology updates or product releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ictionary

-0.94

 constitu

-0.76

oldown

-0.74

 counseling

-0.73

 obligation

-0.71

akespeare

-0.71

cession

-0.70

Cause

-0.70

immigration

-0.69

Jews

-0.69

POSITIVE LOGITS

 teaser

1.46

 screenshots

1.29

 prototype

1.28

 prototypes

1.28

 Prototype

1.18

 IMAGES

1.17

 unveiled

1.16

 preview

1.15

 silhou

1.14

 Concept

1.13

Activations Density 0.586%

phrases related to showcasing or demonstrating new products or technologies

mentions of new technology updates or product releases

No Comments

No Known Activations