INDEX

Explanations

terms related to cybersecurity, hacking, and internet security

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 quæ

-0.71

 feen

-0.65

 canst

-0.62

 laft

-0.61

 fays

-0.60

ftu

-0.60

 beft

-0.60

 lefs

-0.59

 juft

-0.59

<bos>

-0.59

POSITIVE LOGITS

 cybersecurity

0.67

 Cybersecurity

0.63

showAlert

0.58

 vulnerabilities

0.56

 Remediation

0.56

 malware

0.55

 preventive

0.54

 preventative

0.53

 logarith

0.52

 security

0.51

Activations Density 0.510%

terms related to cybersecurity, hacking, and internet security

No Comments

No Known Activations