INDEX

Explanations

proper nouns related to news articles

oai_token-act-pair · gpt-3.5-turbo

sources and their authors in written content

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aterasu

-0.73

Roaming

-0.67

é¾įå¥ĳå£«

-0.66

RGB

-0.64

Ĥİ

-0.64

DragonMagazine

-0.63

gently

-0.61

wagen

-0.60

cknow

-0.57

gars

-0.57

POSITIVE LOGITS

 SHARES

0.89

Posted

0.74

Guest

0.71

 Published

0.70

 Written

0.68

cloneembedreportprint

0.66

 NEWS

0.63

Thu

0.62

 Blog

0.62

ategories

0.62

Activations Density 0.250%

proper nouns related to news articles

sources and their authors in written content

No Comments

No Known Activations