INDEX

Explanations

proper nouns, specifically names of institutions and individuals

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

SpringRunner

-0.59

lorette

-0.50

็จ

-0.49

ResponseWriter

-0.48

每个人

-0.48

ginx

-0.47

SPEAKER

-0.47

 binh

-0.47

åne

-0.47

 MenuView

-0.47

POSITIVE LOGITS

 Brothers

1.10

 brothers

1.01

 Bros

0.99

 family

0.94

 Family

0.93

 BROTHERS

0.91

 frères

0.90

Brothers

0.90

 County

0.88

brothers

0.87

Activations Density 0.536%

proper nouns, specifically names of institutions and individuals

No Comments

No Known Activations