INDEX

Explanations

references to United States locations, organizations, and historical events

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>

-2.74

/**

-1.14

ⓧ

-1.12

-1.11

<?

-1.04

/***

-1.01

<?

-0.97

///**

-0.93

/*

-0.86

/*!

-0.83

POSITIVE LOGITS

Juf

1.09

 véhic

1.06

 maroc

1.06

 lele

1.04

 stockholm

1.03

 délib

1.02

 maneu

1.01

 bandung

1.01

 sovere

1.00

 affor

0.98

Activations Density 0.174%

references to United States locations, organizations, and historical events

No Comments

No Known Activations