INDEX

Explanations

references to people and their geographical or historical significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

IsContent

-0.64

 الحره

-0.60

 offside

-0.59

 estekak

-0.57

 Insee

-0.53

 Saratoga

-0.52

ChildIndex

-0.51

 الرياضيه

-0.51

gemeente

-0.50

 muualla

-0.50

POSITIVE LOGITS

 expedition

0.94

 exploration

0.94

 Exploration

0.88

 expeditions

0.88

 explorations

0.86

 explorers

0.85

Explor

0.83

 explor

0.82

 explorer

0.82

exploration

0.80

Activations Density 0.181%

references to people and their geographical or historical significance

No Comments

No Known Activations