INDEX

Explanations

references to user interface elements and components 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

 <<<<<<<<<<<<<<

-0.83

CloseOperation

-0.80

 onCreateView

-0.76

Hozzáférés

-0.76

matchCondition

-0.71

__':

-0.71

 BorderRadius

-0.67

InSection

-0.67

 مواليد

-0.66

InvalidProtocol

-0.66

POSITIVE LOGITS

 Vogel

0.54

 visual

0.54

 utafitiHapana

0.52

 Flag

0.50

ounid

0.50

 Snyder

0.50

InitStructure

0.49

teenth

0.49

setts

0.48

!(:

0.48

Activations Density 1.108%

references to user interface elements and components in code

No Comments

No Known Activations