INDEX

Explanations

references to various domains of professional and educational settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

PerformLayout

-0.89

RectangleBorder

-0.81

AddTagHelper

-0.75

 ویکی‌پدی

-0.75

 autorytatywna

-0.75

TintMode

-0.74

Chham

-0.73

 SafeMath

-0.72

DoubleQuotes

-0.71

 محفوظة

-0.71

POSITIVE LOGITS

 daraus

0.42

 Résultat

0.42

onActivityResult

0.41

 MaterialApp

0.41

monių

0.40

üksek

0.39

 alike

0.39

levis

0.39

oblastoma

0.39

tope

0.38

Activations Density 0.850%

references to various domains of professional and educational settings

No Comments

No Known Activations