INDEX

Explanations

reported statements and claims made by individuals or officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

SceneManagement

-0.59

 wydaje

-0.50

šla

-0.46

 виправивши

-0.43

argu

-0.43

associated

-0.41

从而

-0.41

 Argu

-0.40

verwijspagina

-0.40

Argu

-0.39

POSITIVE LOGITS

 незавершена

0.71

 dipende

0.69

pexpr

0.69

 BigNumberish

0.67

ⓧ

0.64

ukone

0.64

 Landis

0.64

 Dijo

0.64

ScopeManager

0.63



0.62

Activations Density 0.374%

reported statements and claims made by individuals or officials

No Comments

No Known Activations