INDEX

Explanations

phrases or sentences where the concept of being a part of something (such as human nature, a system, a game, society, culture, etc.) is discussed

oai_token-act-pair · gpt-3.5-turbo

concepts related to human nature and its complexities

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

aughs

-0.78

netflix

-0.70

uador

-0.68

 whiff

-0.62

augh

-0.61

 dodged

-0.60

 candles

-0.59

rians

-0.59

 prostitutes

-0.59

adish

-0.59

POSITIVE LOGITS

 endeavour

0.78

 repertoire

0.75

 arrang

0.75

ĸļ

0.72

 endeavor

0.71

 regimen

0.71

 endeavors

0.70

ortment

0.70

0.68

creation

0.67

Activations Density 0.431%

phrases or sentences where the concept of being a part of something (such as human nature, a system, a game, society, culture, etc.) is discussed

concepts related to human nature and its complexities

No Comments

No Known Activations