INDEX

Explanations

instances of numerical data and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AsUp

-0.72

tagHelperRunner

-0.63

arakhand

-0.63

exitRule

-0.61

}{*}{

-0.61

licone

-0.61

ViewFeatures

-0.55

 medel

-0.53

rrggbb

-0.53

 PopupWindow

-0.52

POSITIVE LOGITS

 дописавши

0.65

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.65

 Vergrößern

0.65

 synag

0.63

</h5>

0.60

 Jardim

0.59

 Trento

0.58

الدراسه

0.58

</blockquote>

0.57

 Cune

0.57

Activations Density 0.021%

instances of numerical data and related terms

No Comments

No Known Activations