INDEX

Explanations

elements related to ancient texts and their authorship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 disambiguazione

-0.64

#+#

-0.61

 الحره

-0.57

 تعدى

-0.53

+#+#

-0.52

 الدولى

-0.49

DrawerToggle

-0.49

 AssemblyCulture

-0.49

enumi

-0.49

gulation

-0.48

POSITIVE LOGITS

Rohy

0.65

 autorytatywna

0.64

andExpect

0.56

Hozzáférés

0.55

 Israel

0.53

WriteBarrier

0.53

fillType

0.53

ArgumentParser

0.53

 Lippen

0.52

 messi

0.51

Activations Density 0.076%

elements related to ancient texts and their authorship

No Comments

No Known Activations