INDEX

Explanations

punctuations and other non-alphanumeric characters

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

initState

-0.68

 gynhyrchwyd

-0.57

XmlRootElement

-0.55

SOUNDBITE

-0.55

љено

-0.54

WriteBarrier

-0.54

 RouterModule

-0.53

AnimationsModule

-0.53

initializeApp

-0.52

WithMany

-0.52

POSITIVE LOGITS

 للمعارف

0.70

參考資料

0.55

complexContent

0.54

 nakalista

0.54

 apologised

0.52

 affez

0.51

utilisons

0.51

 puissent

0.50

Cyfeiriadau

0.50

 potenciales

0.49

Activations Density 0.062%

punctuations and other non-alphanumeric characters

No Comments

No Known Activations