INDEX

Explanations

technical terms related to security vulnerabilities and exploits

oai_token-act-pair · gpt-3.5-turbo

references to vulnerabilities and cybersecurity issues

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

 Connie

-0.86

 canoe

-0.85

chairs

-0.85

 apprentices

-0.85

 Negro

-0.82

rentices

-0.81

Scot

-0.80

 Sundays

-0.79

apolis

-0.77

olit

-0.77

POSITIVE LOGITS

 malware

1.69

 ransomware

1.54

 hackers

1.36

 malicious

1.33

 hacker

1.30

 encrypted

1.27

CVE

1.26

DoS

1.24

 vulnerabilities

1.24

 encryption

1.23

Activations Density 0.664%

technical terms related to security vulnerabilities and exploits

references to vulnerabilities and cybersecurity issues

No Comments

No Known Activations