INDEX

Explanations

technical terms related to computer security vulnerabilities and cyber attacks

oai_token-act-pair · gpt-3.5-turbo

terms related to cybersecurity threats and vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-1.00

chairs

-0.86

 canoe

-0.85

Commission

-0.85

 Negro

-0.85

 apprentices

-0.84

comfort

-0.83

apolis

-0.82

heny

-0.80

rentices

-0.79

POSITIVE LOGITS

 malware

1.86

 ransomware

1.65

 hackers

1.49

 malicious

1.48

 hacker

1.35

CVE

1.33

 vulnerabilities

1.32

 attackers

1.32

 encrypted

1.31

CVE

1.29

Activations Density 0.855%

technical terms related to computer security vulnerabilities and cyber attacks

terms related to cybersecurity threats and vulnerabilities

No Comments

No Known Activations