INDEX

Explanations

mentions or descriptions related to computer security software or hardware

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.53

-0.95

ⓧ

-0.95

/**

-0.95

<?

-0.91

/*

-0.86

<?

-0.79

public

-0.77

/*++

-0.70

#![

-0.68

POSITIVE LOGITS

 maneu

1.92

 affor

1.77

 accla

1.69

 impra

1.67

 increa

1.66

 véhic

1.65

 embodi

1.57

 reluct

1.57

 stockholm

1.57

Juf

1.52

Activations Density 2.165%

mentions or descriptions related to computer security software or hardware

No Comments

No Known Activations