INDEX

Explanations

items related to ratings or evaluations

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.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>

-2.64

/**

-0.89

Autoritní

-0.85

 Савезне

-0.83

ⓧ

-0.81

<?

-0.80

oredCriteria

-0.76

-0.74

SharedCtor

-0.70

Aholisi

-0.70

POSITIVE LOGITS

 bandung

1.50

 jaya

1.31

 jawa

1.26

 Minang

1.23

 lele

1.22

 saar

1.21

 allah

1.16

 increa

1.15

 tulum

1.14

 salat

1.14

Activations Density 0.112%

items related to ratings or evaluations

No Comments

No Known Activations