INDEX

Explanations

references to various U.S. government departments and agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

حياتها

-0.79

 autorytatywna

-0.77

الإنجليزية

-0.75

انجليز

-0.73

awtextra

-0.72

matchCondition

-0.70

Personensuche

-0.67

 Paglinawan

-0.67

حياته

-0.65

üyada

-0.65

POSITIVE LOGITS

 Department

0.61

alige

0.55

DOT

0.52

Department

0.50

 Humanos

0.49

WithMany

0.48

 Bureau

0.48

 Dept

0.47

 Freed

0.46

 Reclamation

0.45

Activations Density 0.382%

references to various U.S. government departments and agencies

No Comments

No Known Activations