INDEX

Explanations

words related to safety and security

oai_token-act-pair · gpt-3.5-turbo

phrases related to safety and security 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

 Alone

-0.72

Textures

-0.71

wic

-0.70

 Beet

-0.70

 oranges

-0.69

 Trees

-0.69

 Balls

-0.68

kas

-0.68

Ö¼

-0.68

nik

-0.67

POSITIVE LOGITS

 confidentiality

1.30

 hygiene

1.26

 privacy

1.23

 security

1.20

 reliability

1.19

 efficacy

1.18

 sustainability

1.16

 sanitation

1.16

 safety

1.13

 stability

1.09

Activations Density 0.140%

words related to safety and security

phrases related to safety and security issues

No Comments

No Known Activations