INDEX

Explanations

terms related to security vulnerabilities, particularly in the context of web development

oai_token-act-pair · gpt-3.5-turbo

references to cross-site vulnerabilities and security 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

PDATE

-0.80

ufact

-0.78

Lago

-0.76

trak

-0.75

ICAN

-0.73

emis

-0.69

Anonymous

-0.69

FUL

-0.66

©¶æ¥µ

-0.64

undai

-0.64

POSITIVE LOGITS

examination

0.73

 contam

0.69

 verte

0.67

cross

0.67

bows

0.67

erences

0.67

bow

0.66

xual

0.65

roads

0.65

ography

0.64

Activations Density 0.061%

terms related to security vulnerabilities, particularly in the context of web development

references to cross-site vulnerabilities and security issues

No Comments

No Known Activations