INDEX

Explanations

mathematical symbols and terms related to algebra and matrix equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

########.

-0.69

rrggbb

-0.66

ISupport

-0.63

Geplaatst

-0.61

 tartalomajánló

-0.54

 Ressources

-0.53

ABAD

-0.50

TRAILING

-0.49

GraphicsUnit

-0.49

gridx

-0.47

POSITIVE LOGITS

 denotes

0.70

 denote

0.68

 désigne

0.62

 quelconque

0.56

 denoting

0.56

 stand

0.55

 dentes

0.54

ooplankton

0.50

 stands

0.50

be

0.49

Activations Density 1.963%

mathematical symbols and terms related to algebra and matrix equations

No Comments

No Known Activations