INDEX

Explanations

terms and phrases related to legal and statistical decisions

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

Words/tokens followed by punctuation

np_acts-logits-general · gemini-2.0-flash

visual acuity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

PreferredItem

-0.62

IsPostBack

-0.55

 autorytatywna

-0.55

IContainer

-0.53

cuadro

-0.53

ⓧ

-0.53

Expedia

-0.51

 للاسماء

-0.49

()?;

-0.49

RefNanny

-0.48

POSITIVE LOGITS

BufferException

0.74

TagMode

0.68

WebVitals

0.67

 utafitiHapana

0.60

TargetException

0.57

AddTagHelper

0.56

neté

0.55

apunov

0.54

mappedBy

0.54

ContentAsync

0.53

Activations Density 14.722%

terms and phrases related to legal and statistical decisions

Words/tokens followed by punctuation

visual acuity

No Comments

No Known Activations