INDEX

Explanations

references to legal or regulatory concepts and terminologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ⓧ

-0.93

روابط

-0.82

Демографія

-0.78

SourceChecksum

-0.78

 continuant

-0.78

 betweenstory

-0.76

tagHelperRunner

-0.76

HasAnnotation

-0.74

 IActionResult

-0.74

 تعدى

-0.74

POSITIVE LOGITS

 Afin

0.54

 endroits

0.50

 midst

0.49

Cube

0.49

lieu

0.48

 contexts

0.47

 lieu

0.47

 批量

0.45

رير

0.44

ladu

0.43

Activations Density 1.304%

references to legal or regulatory concepts and terminologies

No Comments

No Known Activations