INDEX

Explanations

references to a root element in a hierarchical structure or system

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

bukkit

-0.85

 Chamb

-0.80

expandindo

-0.77

 AssemblyTitle

-0.74

verwijspagina

-0.74

 isComment

-0.73

 Flyers

-0.73

ecap

-0.71

 influenza

-0.71

 Belvedere

-0.70

POSITIVE LOGITS

 root

2.38

 Root

2.30

root

2.26

 ROOT

2.20

ROOT

2.15

Root

2.14

 roots

1.95

roots

1.81

 Roots

1.80

Roots

1.72

Activations Density 0.053%

references to a root element in a hierarchical structure or system

No Comments

No Known Activations