INDEX

Explanations

corrections or errors in a text

oai_token-act-pair · gpt-3.5-turbo

mentions of corrections or rectifications in a text

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

Not in Any Lists

No Comments

Negative Logits

atos

-0.97

bang

-0.74

lished

-0.69

axy

-0.67

otor

-0.66

gha

-0.66

thin

-0.65

soDeliveryDate

-0.65

worth

-0.65

achine

-0.63

POSITIVE LOGITS

 misinformation

0.79

é»Ĵ

0.73

Reviewed

0.71

hift

0.71

 inaccur

0.68

 Corrections

0.67

 Correction

0.67

 inaccurate

0.66

onal

0.64

 leveled

0.64

Activations Density 0.028%

corrections or errors in a text

mentions of corrections or rectifications in a text

No Comments

No Known Activations