INDEX

Explanations

words related to legal procedures, imprisonment, and human rights violations

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.56

 bahay

-0.53

 alpes

-0.50

 bandai

-0.50

 meis

-0.49

asserole

-0.48

 sento

-0.48

 gioca

-0.47

 thermomix

-0.47

 ACKNOWLEDGMENTS

-0.47

POSITIVE LOGITS

ⓧ

0.69

İyi

0.59

irsten

0.57

 Magdalen

0.54

 Kild

0.52

/**

0.49

 coerci

0.48

 Pourtant

0.46

 Catharine

0.46

 Denison

0.46

Activations Density 0.428%

words related to legal procedures, imprisonment, and human rights violations

No Comments

No Known Activations