INDEX

Explanations

phrases related to cybersecurity and security vulnerabilities

oai_token-act-pair · gpt-3.5-turbo

references to security-related concepts and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oric

-0.91

kson

-0.76

hyde

-0.75

erers

-0.74

hes

-0.71

ICA

-0.70

oline

-0.70

igion

-0.70

coni

-0.69

liam

-0.68

POSITIVE LOGITS

 vulnerabilities

1.14

 breaches

1.07

 enhancements

0.96

 flaws

0.96

policy

0.95

 advis

0.92

 protocols

0.91

 breach

0.88

 software

0.88

 audits

0.87

Activations Density 0.041%

phrases related to cybersecurity and security vulnerabilities

references to security-related concepts and issues

No Comments

No Known Activations