INDEX

Explanations

proper nouns related to individuals' names

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

inen

-0.69

chest

-0.68

wagen

-0.64

IELD

-0.64

nesota

-0.63

isites

-0.63

 Tinder

-0.63

gered

-0.62

aqu

-0.60

zl

-0.60

POSITIVE LOGITS

rouch

0.87

aldi

0.75

aught

0.73

ursor

0.72

urrency

0.71

elia

0.70

anyon

0.68

illian

0.68

berus

0.67

incinn

0.67

Activations Density 0.242%

proper nouns related to individuals' names

No Comments

No Known Activations