INDEX

Explanations

code elements and identifiers related to online accounts, particularly those involving verification processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

دانشنامهٔ

-0.84

 kirj

-0.66

 hyö

-0.61

fällig

-0.59

 indé

-0.58

utterstock

-0.57

 isComment

-0.57

 onOptions

-0.57

 légiti

-0.57

 contextLoads

-0.56

POSITIVE LOGITS

<bos>

0.60

RegressionTest

0.59

InjectAttribute

0.56

 poveznice

0.49

 nors

0.49

pstead

0.49

transQ

0.48

0.47

Demografia

0.47

///</

0.47

Activations Density 0.156%

code elements and identifiers related to online accounts, particularly those involving verification processes

No Comments

No Known Activations