INDEX

Explanations

specific coding patterns or technical terms associated with programming structure and tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Италијани

-0.82

CardBody

-0.80

principalColumn

-0.80

richTextPanel

-0.76

featureID

-0.75

 tartalomajánló

-0.75

IonicModule

-0.74

 lenker

-0.74

WindowConstants

-0.74

LookAnd

-0.74

POSITIVE LOGITS

 static

1.19

static

0.96

 Static

0.90

Static

0.83

 STATIC

0.82

STATIC

0.80

静态

0.75

MemoryWarning

0.70

reinterpret

0.65

 تضيفلها

0.63

Activations Density 0.006%

specific coding patterns or technical terms associated with programming structure and tags

No Comments

No Known Activations