INDEX

Explanations

programming language keywords related to function and class definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

extAlignment

-0.89

 bezeichneter

-0.88

 تضيفلها

-0.83

IGraphics

-0.78

存于互联网档案馆

-0.78

 متعلقه

-0.77

ViewFeatures

-0.76

例句

-0.75

 ویکی‌آمباردا

-0.74

+#+#

-0.74

POSITIVE LOGITS

public

0.49

 genetically

0.41

 zake

0.41

feof

0.41

getAge

0.40

Discografia

0.40

(`/

0.40

fractive

0.39

 smells

0.39

biór

0.39

Activations Density 0.173%

programming language keywords related to function and class definitions

No Comments

No Known Activations