INDEX

Explanations

structured elements and references within documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Préférences

-0.65

 الحره

-0.58

 Advancement

-0.57

tagHelperRunner

-0.56

 JpaRepository

-0.56

 Stalker

-0.55

 Clic

-0.54

Obrázky

-0.54

 AssemblyCulture

-0.53

 BoxFit

-0.52

POSITIVE LOGITS

 &___

0.54

?}",

0.52

gero

0.51

 }}"></

0.51

pytest

0.50

 welcome

0.50

Tikang

0.49

ddots

0.49

 trous

0.48

se

0.48

Activations Density 0.136%

structured elements and references within documents

No Comments

No Known Activations