INDEX

Explanations

terms and components related to programming frameworks and libraries

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

UnusedPrivate

-0.86

 Whigs

-0.74

 Whig

-0.68

GeneratedValue

-0.67

 Acha

-0.66

 onCancelled

-0.66

 Phry

-0.65

THISDAY

-0.65

 تانيه

-0.63

opcao

-0.62

POSITIVE LOGITS

WriteLiteral

1.61

GetMapping

1.34

migrationBuilder

0.89

 AppCompat

0.89

remarks

0.82

selenium

0.81

ComponentModel

0.81

mybatisplus

0.80

PostMapping

0.74

JButton

0.74

Activations Density 0.008%

terms and components related to programming frameworks and libraries

No Comments

No Known Activations