INDEX

Explanations

programming constructs related to model definitions and imports in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 autorytatywna

-0.57

ьажоргаш

-0.49

tagHelperRunner

-0.48

VIAF

-0.48

AppRoutingModule

-0.48

UpInside

-0.48

 getUrl

-0.47

 faſt

-0.47

 Autorisations

-0.46

yyb

-0.46

POSITIVE LOGITS

 structures

0.49

 estructuras

0.46

 entity

0.46

 objects

0.45

TypedDataSet

0.43

apimachinery

0.43

 entities

0.42

 strutture

0.41

 Codable

0.41

 models

0.40

Activations Density 0.126%

programming constructs related to model definitions and imports in code

No Comments

No Known Activations