INDEX

Explanations

symbols and mathematical expressions related to formulas or equations

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

 estekak

-0.79

verifyException

-0.73

waitKey

-0.67

 שוליים

-0.66

Jeografia

-0.63

InputBorder

-0.62

enumi

-0.62

########.

-0.62

 Quanto

-0.61

 بيها

-0.60

POSITIVE LOGITS

ViewFeatures

0.87

typeorm

0.67

Kaynakça

0.60

IBinder

0.57

ValueGenerated

0.54

AspNet

0.50

 száz

0.49

raltar

0.49

 dahulu

0.49

Activations Density 1.158%

symbols and mathematical expressions related to formulas or equations

No Comments

No Known Activations