INDEX

Explanations

terminology related to the concept of "ground" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Vicenza

-0.95

 HasFactory

-0.83

ⓧ

-0.83

AndEndTag

-0.82

 cytokines

-0.81

 zirc

-0.79

LEncoder

-0.79

 pellic

-0.77

exams

-0.77

 Siren

-0.76

POSITIVE LOGITS

 ground

2.82

 Ground

2.71

Ground

2.60

ground

2.58

 GROUND

2.52

GROUND

2.22

 Grounds

1.72

 grounds

1.71

grounds

1.68

 grond

1.43

Activations Density 0.042%

terminology related to the concept of "ground" in various contexts

No Comments

No Known Activations