INDEX

Explanations

words related to negative traits or behaviors like stupidity, ignorance, arrogance, and incompetence

oai_token-act-pair · gpt-3.5-turbo

negative qualities and criticisms associated with human behavior and societal issues

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

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

nesium

-0.69

 corrid

-0.65

amen

-0.60

iverse

-0.59

amins

-0.59

entin

-0.59

changes

-0.58

ERC

-0.58

 Sabha

-0.58

izable

-0.57

POSITIVE LOGITS

ulence

1.11

 perpetrated

1.07

 perv

1.07

 bordering

1.03

fulness

1.01

iness

0.98

 inherent

0.95

 inflicted

0.94

 abound

0.93

chery

0.92

Activations Density 0.204%

words related to negative traits or behaviors like stupidity, ignorance, arrogance, and incompetence

negative qualities and criticisms associated with human behavior and societal issues

No Comments

No Known Activations