INDEX

Explanations

sentences or fragments punctuated with unusual characters

oai_token-act-pair · gpt-3.5-turbo

sections of text that indicate significant events or announcements

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

Negative Logits

 proport

-0.71

 describ

-0.69

 eleph

-0.69

 citiz

-0.68

 tremend

-0.68

 wiser

-0.65

 footing

-0.65

 artists

-0.64

 unprepared

-0.63

 deceived

-0.63

POSITIVE LOGITS

PHOTOS

0.95

DragonMagazine

0.92

ÂłÂłÂł

0.87

Scroll

0.85

ÂłÂłÂłÂłÂłÂłÂłÂł

0.83

ÂłÂłÂłÂł

0.80

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.80

CVE

0.78

↵

0.77

Federal

0.76

Activations Density 0.642%

sentences or fragments punctuated with unusual characters

sections of text that indicate significant events or announcements

No Known Activations