INDEX

Explanations

lines of code that define packages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 فريبيس

-0.89

principalColumn

-0.68

 ролях

-0.62

webElement

-0.56

 муніципалі

-0.56

Demografie

-0.54

 igång

-0.54

 ElementRef

-0.53

orithmic

-0.53

cillor

-0.53

POSITIVE LOGITS

package

3.73

 package

2.01

 Package

1.71

Package

1.67

 PACKAGE

1.65

PACKAGE

1.49

 packages

1.48

 Packages

1.35

packages

1.23

pkg

1.15

Activations Density 0.018%

lines of code that define packages

No Comments

No Known Activations