INDEX

Explanations

references to tests and testing frameworks in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 hObject

-1.06

bootstrapcdn

-0.96

 oprot

-0.93

mybatisplus

-0.91

writeFieldEnd

-0.84

EndGlobalSection

-0.84

 TextInputType

-0.83

annica

-0.83

 EClass

-0.81

contentLoaded

-0.80

POSITIVE LOGITS

Test

0.76

 Test

0.73

 test

0.67

test

0.63

 example

0.61

 demo

0.58

essai

0.57

getTest

0.55

测试

0.54

文

0.54

Activations Density 0.114%

references to tests and testing frameworks in programming

No Comments

No Known Activations