INDEX

Explanations

names of celebrities or characters being portrayed as other celebrities or characters

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>

-0.91

 Paglinawan

-0.72

 kasarigan

-0.68

GEBURTSDATUM

-0.68

 nogen

-0.62

 ország

-0.61

تقاوى

-0.61

 about

-0.58

Становништво

-0.57

styleType

-0.57

POSITIVE LOGITS

 exé

1.63

 prouve

1.53

 rafra

1.45

 dépasse

1.44

 trouvera

1.43

 prétend

1.42

 renfer

1.41

 pixabay

1.40

 prendra

1.39

 représ

1.38

Activations Density 0.102%

names of celebrities or characters being portrayed as other celebrities or characters

No Comments

No Known Activations