INDEX

Explanations

keywords related to lack of understanding or confusion

oai_token-act-pair · gpt-3.5-turbo

terms related to clarity and certainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

atern

-0.75

Bey

-0.68

heimer

-0.67

nie

-0.66

Interstitial

-0.65

nar

-0.64

 Abram

-0.63

Il

-0.62

Particip

-0.62

cele

-0.62

POSITIVE LOGITS

 clarity

1.27

0.92

iness

0.89

mares

0.82

 assurance

0.77

fully

0.74

MX

0.73

wcs

0.73

assetsadobe

0.72

fulness

0.72

Activations Density 0.011%

keywords related to lack of understanding or confusion

terms related to clarity and certainty

No Comments

No Known Activations