INDEX

Explanations

names or entities related to 'Ad'

oai_token-act-pair · gpt-3.5-turbo

references to individuals or entities associated with "Ad"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 gears

-0.67

wagen

-0.66

¬¼

-0.66

taboola

-0.63

 pancakes

-0.61

 sidewalks

-0.60

ibaba

-0.60

 intersections

-0.60

 unchecked

-0.59

ĨĴ

-0.59

POSITIVE LOGITS

aline

0.76

ause

0.75

minus

0.72

Ake

0.70

oli

0.68

anamo

0.67

 Samar

0.67

ucl

0.65

lie

0.65

bia

0.65

Activations Density 0.100%

names or entities related to 'Ad'

references to individuals or entities associated with "Ad"

No Comments

No Known Activations