INDEX

Explanations

categories and classifications related to geographical locations and biological taxonomy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

óg

-0.51

 cref

-0.49

ibatis

-0.48

pé

-0.48

 нала

-0.47

 uniformed

-0.47

 vellum

-0.46

httphttps

-0.46

 lege

-0.46

 Shores

-0.45

POSITIVE LOGITS

SpringRunner

0.72

subpackage

0.68

 désolés

0.68

Бележки

0.67

DrawerToggle

0.65

NameInMap

0.63

extAlignment

0.62

 ApiException

0.61

 AspNetCore

0.59

 الحره

0.58

Activations Density 0.736%

categories and classifications related to geographical locations and biological taxonomy

No Comments

No Known Activations