INDEX

Explanations

terms related to cyber security and digital threats

oai_token-act-pair · gpt-3.5-turbo

references to cybersecurity topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Clement

-0.80

 Pearce

-0.71

erer

-0.71

ered

-0.71

 LINE

-0.70

 Browne

-0.69

 Taste

-0.69

 Jinn

-0.68

IELD

-0.68

++++++++++++++++

-0.66

POSITIVE LOGITS

netic

1.51

punk

1.23

attacks

1.07

crime

1.02

security

1.01

activ

0.92

crim

0.92

 warfare

0.91

bull

0.90

criminal

0.90

Activations Density 0.028%

terms related to cyber security and digital threats

references to cybersecurity topics

No Comments

No Known Activations