INDEX

Explanations

text related to legal cases, law enforcement, and government actions

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.0.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>

-3.13

ⓧ

-1.19

/**

-1.13

-1.11

<?

-1.07

/*

-0.99

<?

-0.91

/***

-0.86

/*++

-0.84

///**

-0.84

POSITIVE LOGITS

 maneu

1.95

 affor

1.90

 accla

1.83

 increa

1.80

 impra

1.70

 stockholm

1.68

 reluct

1.67

 emphat

1.67

 inev

1.66

 Manufact

1.64

Activations Density 3.242%

text related to legal cases, law enforcement, and government actions

No Comments

No Known Activations