INDEX

Explanations

elements related to structured content, such as numerical data and formatted sections

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

webElementXpaths

-0.87

AddTagHelper

-0.80

hyrchwyd

-0.68

脚注の使い方

-0.64

assertRaises

-0.62

]")]

-0.61

tagHelperRunner

-0.60

 typelib

-0.58

 calendriers

-0.56

 ModelExpression

-0.56

POSITIVE LOGITS

 kasarigan

0.62

SafeAreaView

0.56

CloseHandle

0.54

DrawerToggle

0.51

GenerationType

0.50

DNEY

0.49

audiovisuel

0.49

Alike

0.48

APORE

0.48

󠁿

0.46

Activations Density 0.502%

elements related to structured content, such as numerical data and formatted sections

No Comments

No Known Activations