INDEX

Explanations

technical terms and variations related to "comp" or "complementary."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

AutoScaleMode

-0.81

(!__

-0.77

EndTag

-0.75

UVWXYZ

-0.72

 minOccurs

-0.71

 Jule

-0.70



-0.70

iriman

-0.70

Lag

-0.70

 trữ

-0.70

POSITIVE LOGITS

Comp

1.25

COM

1.23

COMP

1.23

 COMP

1.20

COM

1.15

comp

1.15

 Comp

1.14

 comps

1.05

Com

1.04

omp

1.02

Activations Density 0.192%

technical terms and variations related to "comp" or "complementary."

No Comments

No Known Activations