INDEX

Explanations

terms related to computer security

oai_token-act-pair · gpt-3.5-turbo

terms related to security vulnerabilities and issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

-0.97

kson

-0.83

hes

-0.79

ICA

-0.70

 Kinn

-0.67

iton

-0.65

shire

-0.65

arget

-0.65

zl

-0.64

inal

-0.64

POSITIVE LOGITS

 vulnerabilities

0.85

 advis

0.83

 breaches

0.83

policy

0.81

 clearance

0.80

 flaws

0.78

 guards

0.78

 posture

0.78

 lapse

0.76

 enforcement

0.75

Activations Density 0.022%

terms related to computer security

terms related to security vulnerabilities and issues

No Comments

No Known Activations