INDEX

Explanations

terms related to cybersecurity and hacking techniques

oai_token-act-pair · gpt-3.5-turbo

terms related to hacking and cybersecurity threats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 graduating

-0.72

 resid

-0.68

 Okin

-0.67

 masc

-0.66

Bib

-0.64

enegger

-0.64

 revital

-0.63

inement

-0.62

 Dayton

-0.62

 sublime

-0.62

POSITIVE LOGITS

Crypt

1.41

DoS

1.32

 malware

1.26

 encryption

1.25

crypt

1.23

Torrent

1.22

Secure

1.22

VPN

1.18

Keys

1.17

 encrypt

1.14

Activations Density 0.291%

terms related to cybersecurity and hacking techniques

terms related to hacking and cybersecurity threats

No Comments

No Known Activations