INDEX

Explanations

terms and references related to geographical and cultural attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 coroa

-0.39

 potrebbero

-0.38

 datter

-0.36

 hayas

-0.36

 Städte

-0.35

șe

-0.35

 diduga

-0.35

 Ehre

-0.35

 flota

-0.35

 timmar

-0.34

POSITIVE LOGITS

 autorytatywna

0.76

transQ

0.66

jsxFileName

0.63

BeginContext

0.63

 Administrativna

0.62

GOTREF

0.62

rrggbb

0.60

aarrggbb

0.60

باردا

0.60

úgó

0.59

Activations Density 0.281%

terms and references related to geographical and cultural attributes

No Comments

No Known Activations