INDEX

Explanations

phrases related to software vulnerabilities

oai_token-act-pair · gpt-3.5-turbo

references to security vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

kos

-0.88

zos

-0.87

icle

-0.82

ľ

-0.81

omer

-0.80

agher

-0.78

ghai

-0.75

omers

-0.75

verett

-0.75

arel

-0.73

POSITIVE LOGITS

ulnerability

1.28

 vulnerability

1.27

 vulnerabilities

1.21

ulner

1.18

CVE

1.17

 vulner

1.13

ulnerable

1.05

CVE

0.95

 vulnerable

0.87

 flaw

0.86

Activations Density 0.007%

phrases related to software vulnerabilities

references to security vulnerabilities

No Comments

No Known Activations