INDEX

Explanations

vulnerable words or phrases related to security and potential threats

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.11

/***

-0.76

///**

-0.61

 للمعارف

-0.61

Referencie

-0.59

/**

-0.57

ඒ

-0.57

насе

-0.57

 repatri

-0.56

EndProject

-0.56

POSITIVE LOGITS

 vulnerability

1.23

 Vulnerable

1.20

 vulnerable

1.16

 Vulnerability

1.14

 vulnerabilities

1.10

VUL

1.07

 bourgeo

0.97

 levis

0.96

 italia

0.95

 milano

0.94

Activations Density 0.285%

vulnerable words or phrases related to security and potential threats

No Comments

No Known Activations