INDEX

Explanations

references to alternative options or comparisons in various contexts

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

WebElementEntity

-0.64

DIPSETTING

-0.62



-0.50

$_['

-0.49

первых

-0.48

 surla

-0.48

تقاوى

-0.47

numerusform

-0.46

mobileqq

-0.45

TintMode

-0.45

POSITIVE LOGITS

 дописавши

0.73

 validamos

0.70

 للاسماء

0.67

)‏

0.64

 вікі

0.61

]();

0.59

InstrumentedTest

0.58

 nahilalakip

0.58

 MessageBoxIcon

0.57

Eſ

0.56

Activations Density 0.246%

references to alternative options or comparisons in various contexts

No Comments

No Known Activations