INDEX

Explanations

numerical values or statistics in the text

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

Controllo

-0.59

Спољашње

-0.56

columnHeader

-0.54

apest

-0.52

Erreferentziak

-0.51

elif

-0.49

Del

-0.48

摩

-0.48

ganet

-0.48

ksessa

-0.48

POSITIVE LOGITS

 couverts

0.62

CloseOperation

0.62

Espèce

0.62

 Nacionales

0.61

 idéia

0.58

0.56

 engraçadas

0.54

 GeoNames

0.54

 ujednoznacz

0.53

 bañ

0.53

Activations Density 0.334%

numerical values or statistics in the text

No Comments

No Known Activations