INDEX

Explanations

indications of updating or correcting information

oai_token-act-pair · gpt-3.5-turbo

references to updates or changes in content

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

pmwiki

-0.79

soDeliveryDate

-0.75

ulhu

-0.75

pill

-0.71

baum

-0.71

ymm

-0.71

Anth

-0.71

zees

-0.70

æ©

-0.69

ãĤ¼ãĤ¦ãĤ¹

-0.69

POSITIVE LOGITS

 updates

0.84

 updated

0.81

 whereabouts

0.74

 revised

0.73

 corrected

0.72

 details

0.72

 chron

0.71

 arrival

0.71

 timeline

0.71

 timetable

0.71

Activations Density 0.128%

indications of updating or correcting information

references to updates or changes in content

No Known Activations