INDEX

Explanations

references to research studies and program evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

SequentialGroup

-0.92

 resourceCulture

-0.67

InputBorder

-0.67

didSet

-0.66

+#+

-0.63

LayoutConstraint

-0.62

脚注の使い方

-0.62

 AssemblyCompany

-0.61

 BoxDecoration

-0.59

حوالہ

-0.59

POSITIVE LOGITS

OGND

0.61

 समीक्षाओं

0.60

 AspNetCore

0.57

 sèche

0.54

tgär

0.53

getMenuInflater

0.52

 tartalomajánló

0.50

entibus

0.47

onViewCreated

0.47

 sessionFactory

0.46

Activations Density 0.881%

references to research studies and program evaluations

No Comments

No Known Activations