INDEX

Explanations

references to awards, recognitions, or distinctions related to individuals or entities

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

 gynhyrchwyd

-0.90

sizeCache

-0.86

GraphicsUnit

-0.85

 Réponses

-0.77

 المعيارى

-0.73

 Мексичка

-0.72

andExpect

-0.71

AnimationsModule

-0.70

 nahilalakip

-0.69

 تضيفلها

-0.65

POSITIVE LOGITS

 diyor

0.44

 AUSSI

0.44

ecm

0.43

ivar

0.43

lasty

0.42

 their

0.41

its

0.40

glVertex

0.39

 ihres

0.39

asikan

0.39

Activations Density 1.584%

references to awards, recognitions, or distinctions related to individuals or entities

No Comments

No Known Activations