INDEX

Explanations

router-related terms and mention of attacks or vulnerabilities

oai_token-act-pair · gpt-3.5-turbo

terms related to network routers and their security vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.94

orical

-0.78

itate

-0.77

iatrics

-0.73

idth

-0.72

issance

-0.71

orically

-0.70

itated

-0.69

isine

-0.68

oric

-0.67

POSITIVE LOGITS

 router

1.20

 routers

1.18

 Router

1.06

oute

0.91

 connectivity

0.81

 networking

0.78

layer

0.78

 routing

0.78

VPN

0.76

eering

0.76

Activations Density 0.052%

router-related terms and mention of attacks or vulnerabilities

terms related to network routers and their security vulnerabilities

No Comments

No Known Activations