INDEX

Explanations

terms related to measurements, specifically weights and quantities

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

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

LookAnd

-0.79

parsedMessage

-0.75

SharedCtor

-0.68

TypedDataSet

-0.67

AutoresizingMask

-0.66

AccessorTable

-0.65

原始内容存档于

-0.64

ksikon

-0.64

 AssemblyCulture

-0.59

 متعلقه

-0.59

POSITIVE LOGITS

kg

0.85

kg

0.85

 ounces

0.83

 kilogram

0.81

 kilograms

0.79

 grams

0.74

oz

0.74

Kg

0.74

 gram

0.72

 ounce

0.72

Activations Density 0.352%

terms related to measurements, specifically weights and quantities

No Comments

No Known Activations