INDEX

Explanations

various numerical references and descriptions in lists or tables

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-3.19

ⓧ

-1.09

Autoritní

-0.97

/**

-0.85

<?

-0.85

contentLoaded

-0.79

 Wikiseite

-0.77

/*

-0.74

########.

-0.73

Datuak

-0.72

POSITIVE LOGITS

 lele

1.21

 antik

1.19

 saar

1.18

 optik

1.15

 makro

1.15

 akut

1.12

 meis

1.11

 overla

1.11

 Strukt

1.10

 alkoh

1.10

Activations Density 0.189%

various numerical references and descriptions in lists or tables

No Comments

No Known Activations