INDEX

Explanations

terms related to cyber security and cyber attacks

oai_token-act-pair · gpt-3.5-turbo

terms related to cyber threats and attacks

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Clement

-0.80

erer

-0.73

 Taste

-0.70

 Zucker

-0.69

ered

-0.69

 Towns

-0.64

 Bottle

-0.64

 LINE

-0.63

 Pearce

-0.63

 Flav

-0.62

POSITIVE LOGITS

netic

1.60

attacks

1.34

crime

1.30

punk

1.30

security

1.28

crim

1.17

threat

1.16

bull

1.13

criminal

1.12

attack

1.11

Activations Density 0.019%

terms related to cyber security and cyber attacks

terms related to cyber threats and attacks

No Comments

No Known Activations