INDEX

Explanations

references to social interactions or dialogues

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

 AssemblyTitle

-0.52

 ویکی‌پدی

-0.49

bpy

-0.47

//

-0.45

@"/

-0.45

χο

-0.44

 canton

-0.44

BoxShadow

-0.44

VersionUID

-0.44

 McCon

-0.42

POSITIVE LOGITS

 myſelf

0.76

 myself

0.75

GEBURTSDATUM

0.73

RectangleBorder

0.67

myself

0.67

tagHelperRunner

0.65

دانشنامهٔ

0.61

 linkovi

0.59

сылкі

0.58

AsUp

0.57

Activations Density 0.301%

references to social interactions or dialogues

No Comments

No Known Activations