INDEX

Explanations

references to base class functionalities and inheritance in code

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

elemField

-0.62

ValueStyle

-0.52

canestro

-0.52

ilden

-0.49

Награды

-0.48

eser

-0.48

 utafitiHapana

-0.48

odacty

-0.47

jooq

-0.46

Pul

-0.45

POSITIVE LOGITS

Superclass

0.82

abstractmethod

0.81

XmlAccessorType

0.75

 RIPRODUZIONE

0.74

inheritdoc

0.72

inherit

0.70

Hozzáférés

0.68

inherits

0.68

Override

0.67

继承

0.67

Activations Density 0.204%

references to base class functionalities and inheritance in code

No Comments

No Known Activations