INDEX

Explanations

references to mapping concepts or related terms

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

HideInInspector

-0.79

serviceWorker

-0.76

 AssemblyCompany

-0.72

-0.69

Predecesor

-0.68

ільки

-0.67

はじめに

-0.67

 toute

-0.67

liance

-0.66

 Nghi

-0.65

POSITIVE LOGITS

 maps

1.95

map

1.77

 Maps

1.70

Map

1.62

MAP

1.55

map

1.52

Map

1.45

maps

1.41

Maps

1.39

MAP

1.33

Activations Density 0.052%

references to mapping concepts or related terms

No Comments

No Known Activations