INDEX

Explanations

proper nouns related to individuals or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of people and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

iden

-0.81

icum

-0.75

alia

-0.71

icro

-0.68

opsis

-0.68

esthes

-0.68

alysis

-0.67

uning

-0.66

chers

-0.66

akedown

-0.66

POSITIVE LOGITS

vernment

1.04

glers

0.89

ORGE

0.83

 Pengu

0.81

irlfriend

0.80

CHQ

0.74

iants

0.72

raphic

0.72

finger

0.71

stones

0.70

Activations Density 0.074%

proper nouns related to individuals or entities

proper nouns, specifically names of people and organizations

No Comments

No Known Activations