INDEX

Explanations

phrases related to comparison or evaluation

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

 dispen

-1.32

fta

-1.31

 wien

-1.31

fuf

-1.30

fte

-1.29

 accla

-1.29

 wherea

-1.28

 increa

-1.27

 secon

-1.27

 volunte

-1.26

POSITIVE LOGITS

<bos>

0.67

 what

0.58

 jemals

0.56

nor

0.56

how

0.56

Trichloroethane

0.54

GOTREF

0.53

<tfoot>

0.53

انيف

0.52

setToolTip

0.52

Activations Density 0.372%

phrases related to comparison or evaluation

No Comments

No Known Activations