INDEX

Explanations

questions and interrogative phrases

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

ⓧ

-0.94

<bos>

-0.91

Lmfao

-0.75

<?

-0.73

Hahahahaha

-0.71

Hahah

-0.69

/**

-0.69

Lma

-0.69

Noice

-0.62

-0.60

POSITIVE LOGITS

 lemp

0.94

 Valentín

0.93

 quoc

0.91

 ananas

0.88

 paradiso

0.88

 barbacoa

0.88

 cristo

0.86

 thuy

0.85

 nuoc

0.85

 paloma

0.85

Activations Density 0.107%

questions and interrogative phrases

No Comments

No Known Activations