INDEX

Explanations

references to dragons

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

homonymie

-0.61

 للاسماء

-0.59

AndroidJUnit

-0.58

serviceWorker

-0.56

ftagPool

-0.56

BufferException

-0.56

TextInputLayout

-0.55

ariste

-0.54

 كومونز

-0.53

>>();

-0.53

POSITIVE LOGITS

 dragon

1.30

 Dragon

1.29

Dragon

1.26

dragon

1.23

 dragons

1.20

Dragons

1.16

 Dragons

1.15

 DRAGON

1.13

dragons

1.03

 Khart

0.86

Activations Density 0.092%

references to dragons

No Comments

No Known Activations