INDEX

Explanations

references or suggestions related to additional content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sucedido

-0.53

 spagno

-0.52

 singoli

-0.52

 värld

-0.51

slidesPer

-0.51

 schermata

-0.51

 llorando

-0.51

 alone

-0.51

Myself

-0.50

 duod

-0.50

POSITIVE LOGITS

最快更新

0.86

Datuak

0.75

⋙

0.73

 Infórmanos

0.73

دانشنامهٔ

0.71

 AssemblyTitle

0.70

 مشين

0.70

 utafitiHapana

0.68

__':

0.67

Personendaten

0.66

Activations Density 0.027%

references or suggestions related to additional content

No Comments

No Known Activations