INDEX

Explanations

components or modules in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

DotNetBar

-0.47

スナー

-0.47

 chantier

-0.47

 iVar

-0.47

var

-0.46

ambar

-0.46

tagHelper

-0.46

 tirantes

-0.45

 hands

-0.43

amb

-0.43

POSITIVE LOGITS

imports

0.80

NgModule

0.75

 NgModule

0.73

styleUrls

0.67

 AppModule

0.65

 ExecuteAsync

0.63

providers

0.61

CommonModule

0.60

 Modules

0.60

ceries

0.59

Activations Density 0.022%

components or modules in a programming context

No Comments

No Known Activations