INDEX

Explanations

the various forms of the word "use" in different contexts

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

"Used to" and its variations

np_acts-logits-general · gemini-2.0-flash

indicates past use and purpose

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ViewFeatures

-1.04

 ExecuteAsync

-0.88

ArrowToggle

-0.86

Personensuche

-0.84

WebVitals

-0.83

GeoNames

-0.82

 houſe

-0.79

 linkovi

-0.79

elemField

-0.79

 Majefty

-0.78

POSITIVE LOGITS

 Uses

0.61

age

0.61

 uses

0.57

に使

0.57

FUL

0.56

fully

0.55

fulness

0.54

日閲覧

0.54

 USES

0.53

用途

0.53

Activations Density 0.242%

the various forms of the word "use" in different contexts

"Used to" and its variations

indicates past use and purpose

No Comments

No Known Activations