INDEX

Explanations

markers of structure or formatting in text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ScopeManager

-0.77

DoubleQuotes

-0.75

enderror

-0.72

enumi

-0.70

الثة

-0.68

numerusform

-0.62

UrlResolution

-0.60

 whiteColor

-0.59

::_('

-0.57

FunctionFlags

-0.56

POSITIVE LOGITS

queryInterface

0.74

︎

0.71

Portail

0.70

 arbej

0.64

 parlour

0.64

:✨

0.62

 parlor

0.61

getDescriptor

0.61

SharedDtor

0.61

 thofe

0.60

Activations Density 0.196%

markers of structure or formatting in text

No Comments

No Known Activations

markers of structure or formatting in text

No Comments

No Known Activations