INDEX

Explanations

references to process or service configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

nameof

-0.57

Guten

-0.56

 Wohl

-0.55

 Amos

-0.54

abrigo

-0.53

CellStyle

-0.51

 Locker

-0.50

 quartile

-0.49

Groß

-0.49

Reporte

-0.48

POSITIVE LOGITS

 विश्वसनीयता

0.71

abestanden

0.67

 {}),

0.65

 kasarigan

0.63

AddTagHelper

0.63

CloseOperation

0.61

complexContent

0.61

MigrationBuilder

0.60

 NgModule

0.60

Искәрмәләр

0.60

Activations Density 0.129%

references to process or service configurations

No Comments

No Known Activations