INDEX

Explanations

repeated patterns or structures within data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

-0.45

||

-0.42

hdashline

-0.42

kto

-0.40

 phong

-0.38

-*

-0.38

фу

-0.37

 eficacia

-0.37

 huden

-0.37

starch

-0.37

POSITIVE LOGITS

verwijspagina

0.99

 utafitiHapana

0.94

 autorytatywna

0.93

 GenerationType

0.90

rungsseite

0.89

ViewImports

0.89

queryInterface

0.86

 bağlantılar

0.86

 للاسماء

0.83

 المعيارى

0.83

Activations Density 0.882%

repeated patterns or structures within data

No Comments

No Known Activations