INDEX

Explanations

references to military training and operations

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>

-1.92

lateinit

-0.66

Попис

-0.65

<?

-0.64

/*

-0.60

setDo

-0.60

intios

-0.60

таратура

-0.57

السكان

-0.57

ⓧ

-0.57

POSITIVE LOGITS

 Minang

1.83

 Khart

1.57

Juf

1.51

 Banjar

1.49

 Keny

1.48

 Pekan

1.48

 Karang

1.42

 saar

1.42

 Palembang

1.41

 Muhamma

1.39

Activations Density 5.631%

references to military training and operations

No Comments

No Known Activations