INDEX

Explanations

proper nouns related to locations or people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names associated with locations and individuals

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

retty

-0.92

ichick

-0.83

idable

-0.80

INTON

-0.74

inqu

-0.73

estern

-0.70

okia

-0.68

ablishment

-0.68

cohol

-0.68

GAN

-0.68

POSITIVE LOGITS

leness

0.84

erer

0.78

elf

0.75

rates

0.74

ures

0.71

matter

0.68

lighting

0.67

erers

0.67

rate

0.66

shire

0.64

Activations Density 0.062%

proper nouns related to locations or people

proper nouns, particularly names associated with locations and individuals

No Comments

No Known Activations