INDEX

Explanations

mathematical expressions or terms related to limits and functions in an abstract mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

rungsseite

-0.68

ImageContext

-0.68

 kaarangay

-0.67

RegressionTest

-0.63

ValueStyle

-0.62

 utafitiHapana

-0.55

ībā

-0.54

afficheront

-0.53

ActivityCompat

-0.53

writeFieldEnd

-0.51

POSITIVE LOGITS

ViewFeatures

0.58

\}_{

0.55

 Zusch

0.53

 الاطلاع

0.52

DispatchToProps

0.52

 Commentaires

0.50

__(/*!

0.50

 alamu

0.48

othed

0.48

zik

0.47

Activations Density 1.246%

mathematical expressions or terms related to limits and functions in an abstract mathematical context

No Comments

No Known Activations