INDEX

Explanations

occurrences of specific technical attributes or properties used in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Datuak

-0.96

 kaarangay

-0.89

afficheront

-0.88

bewerken

-0.83

 resourceCulture

-0.83

<?

-0.82

قایناق‌لار

-0.81

Personendaten

-0.78

ThroughAttribute

-0.77

oredCriteria

-0.77

POSITIVE LOGITS

 CreateTagHelper

1.88

TabIndex

0.81

templateUrl

0.71

millimeters

0.70

Descriptors

0.64

ClientSize

0.62

 BoxDecoration

0.62

 AssemblyTitle

0.62

BeginInit

0.60

defineProperty

0.57

Activations Density 0.018%

occurrences of specific technical attributes or properties used in code

No Comments

No Known Activations