INDEX

Explanations

code structures and syntax elements, particularly related to defining classes and methods

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

 replaced

-0.51

-0.48

 promu

-0.44

λ

-0.43

ization

-0.43

telli

-0.43

misi

-0.43

ge

-0.42

sproz

-0.42

ized

-0.42

POSITIVE LOGITS

 ujednoznacz

0.83

 Réponses

0.80

 мәкал

0.79

 Audiodateien

0.74

Personensuche

0.73

ьаж

0.71

دانشنامهٔ

0.69

uxxxx

0.68

PreferredItem

0.67

 समीक्षाओं

0.66

Activations Density 0.009%

code structures and syntax elements, particularly related to defining classes and methods

No Comments

No Known Activations