INDEX

Explanations

text related to cybersecurity vulnerabilities

oai_token-act-pair · gpt-3.5-turbo

terms related to vulnerabilities in software or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Īè

-0.68

arts

-0.68

ople

-0.68

agues

-0.67

tops

-0.67

lled

-0.66

atories

-0.65

cellaneous

-0.64

 Mill

-0.64

 Ange

-0.64

POSITIVE LOGITS

 vulnerability

3.78

 vulnerabilities

3.11

ulnerability

2.61

ulner

1.99

 vulner

1.90

CVE

1.82

 vulnerable

1.79

 susceptibility

1.76

 weakness

1.73

 resilience

1.65

Activations Density 0.012%

text related to cybersecurity vulnerabilities

terms related to vulnerabilities in software or systems

No Comments

No Known Activations