INDEX

Explanations

references to time periods, specifically late and early parts of centuries or decades

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 EconPapers

-0.72

bpy

-0.65

 disponibilités

-0.64

 فريبيس

-0.62

="@+

-0.62

 chré

-0.61

 Parac

-0.61

 cref

-0.61

脚注の使い方

-0.61

 ainfi

-0.61

POSITIVE LOGITS

 late

1.11

 delayed

0.96

Delayed

0.81

delayed

0.80

 Delayed

0.78

 early

0.75

mid

0.65

UnitTesting

0.63

 postponed

0.63

Coordonnées

0.63

Activations Density 0.157%

references to time periods, specifically late and early parts of centuries or decades

No Comments

No Known Activations