INDEX

Explanations

programming terminology related to data persistence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ukone

-0.76

rouvez

-0.63

 getNombre

-0.62

 menetap

-0.61

pellier

-0.61

HasOne

-0.58

transQ

-0.58

hyr

-0.58

례

-0.58

 artificiales

-0.57

POSITIVE LOGITS

tvguidetime

0.86

MathML

0.83

Math

0.82

 GenerationType

0.78

 arşivlendi

0.73

 оригіналу

0.72

PageIndex

0.71

LayoutStyle

0.70

wapV

0.69

MigrationBuilder

0.68

Activations Density 0.024%

programming terminology related to data persistence

No Comments

No Known Activations