INDEX

Explanations

technical terms related to security vulnerabilities

oai_token-act-pair · gpt-3.5-turbo

terms related to cybersecurity vulnerabilities and exploits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ikk

-0.80

thumbnails

-0.79

essional

-0.77

ohydrate

-0.75

iatrics

-0.73

mates

-0.71

addle

-0.71

eree

-0.71

âĢ¢âĢ¢

-0.70

cellence

-0.70

POSITIVE LOGITS

CVE

1.27

CVE

1.19

 vulnerabilities

1.10

WARE

1.08

 hackers

1.07

 malware

1.06

ulner

1.03

 hacker

1.01

 exploit

0.99

ulnerability

0.98

Activations Density 0.149%

technical terms related to security vulnerabilities

terms related to cybersecurity vulnerabilities and exploits

No Comments

No Known Activations