INDEX

Explanations

terms related to cybersecurity and cyber attacks

oai_token-act-pair · gpt-3.5-turbo

terms related to cyberattacks and cybersecurity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Flav

-0.79

 Clement

-0.77

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

-0.76

ered

-0.76

IELD

-0.74

 Jinn

-0.74

 LINE

-0.73

 Pearce

-0.70

 Taste

-0.69

UCT

-0.69

POSITIVE LOGITS

netic

1.39

punk

1.21

attacks

1.02

crime

0.93

assault

0.91

security

0.89

terrorism

0.88

intelligence

0.86

attack

0.86

prus

0.86

Activations Density 0.016%

terms related to cybersecurity and cyber attacks

terms related to cyberattacks and cybersecurity

No Comments

No Known Activations