INDEX

Explanations

references to American institutions, organizations, or governmental bodies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

enumi

-0.62

DeleteBehavior

-0.58

 Trouver

-0.58

fromnode

-0.57

ijuana

-0.56

 ComVisible

-0.55

parseFloat

-0.55

 ergon

-0.55

GEBURTSDATUM

-0.55

deviantart

-0.54

POSITIVE LOGITS

Portail

0.68

migrationBuilder

0.63

 National

0.59

intellij

0.57

脚注の使い方

0.57

 poveznice

0.55

Искәрмәләр

0.55

tagHelperRunner

0.54

Попис

0.54

Referanser

0.53

Activations Density 1.029%

references to American institutions, organizations, or governmental bodies

No Comments

No Known Activations