INDEX

Explanations

terms related to measurement or quantification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ConstraintMaker

-0.66

LookAnd

-0.61

 Parcelable

-0.58

 Meksiku

-0.52

TagHelpers

-0.52

 تضيفلها

-0.50

elemField

-0.50

Földrajzportál

-0.50

 colorWith

-0.49

hawk

-0.48

POSITIVE LOGITS

Portail

0.81

of

0.75

makeText

0.64

waitKey

0.57

enterOuterAlt

0.55

setupUi

0.55

ของ

0.54

PageRoute

0.54

stylers

0.54

osa

0.53

Activations Density 1.027%

terms related to measurement or quantification

No Comments

No Known Activations