INDEX

Explanations

code and technical terminology related to protocol buffers and Swift programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.48

yl

-0.42

en

-0.39

 fumée

-0.38

en

-0.38

 AssemblyCompany

-0.37

 braccia

-0.37

POSITIVE LOGITS

 EconPapers

0.94

 autorytatywna

0.86

 kasarigan

0.85

 Roskov

0.83

 незавершена

0.77

ंदीखरीदारी

0.75

 noDo

0.70

OGND

0.69

Personensuche

0.69

webElementXpaths

0.68

Activations Density 0.519%

code and technical terminology related to protocol buffers and Swift programming

No Comments

No Known Activations