INDEX

Explanations

attributes related to product features and material specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 blankets

-0.55

CreateModel

-0.54

imetry

-0.49

Wikis

-0.48

टे

-0.46

毯

-0.46

 professionali

-0.45

duk

-0.43

 plasmids

-0.43

 leggi

-0.42

POSITIVE LOGITS

 Roskov

0.70

#+#

0.70

 <=",

0.69

 Orrell

0.68

MigrationBuilder

0.65

 समीक्षक

0.65

DataAnnotations

0.63

 Wiktionnaire

0.62

 onOptions

0.61

ंदीखरीदारी

0.61

Activations Density 0.078%

attributes related to product features and material specifications

No Comments

No Known Activations