INDEX

Explanations

references to exceptions or errors in code execution

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

SourceChecksum

-0.85

تقاوى

-0.78

ValueStyle

-0.72

ingeki

-0.70

transQ

-0.69

HomeAsUpEnabled

-0.69

 BoxFit

-0.67

 Monfieur

-0.66

]")]

-0.66

 protoimpl

-0.64

POSITIVE LOGITS

 driver

0.66

 Selenium

0.64

WebDriver

0.63

 selenium

0.63

webdriver

0.62

 WebElement

0.61

driver

0.59

 browser

0.59

Selenium

0.59

openqa

0.57

Activations Density 0.161%

references to exceptions or errors in code execution

No Comments

No Known Activations