INDEX

Explanations

inclusive and structured elements related to mathematical formatting

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 limit

-0.52

 thread

-0.49

legging

-0.49

кономі

-0.49

irmer

-0.48

 position

-0.48

endpush

-0.47

 road

-0.47

kirchen

-0.47

 supply

-0.47

POSITIVE LOGITS

 CreateTagHelper

1.19

BeginContext

0.93

 ModelExpression

0.91

":[{

0.88

\{\\

0.85

verwijspagina

0.84

 Taktlose

0.83

:"-"`

0.82

Tembelea

0.82

 дописавши

0.81

Activations Density 0.061%

inclusive and structured elements related to mathematical formatting

No Comments

No Known Activations