INDEX

Explanations

words and terms related to "co" or "cooperation" concepts, including variations of the prefix "co" in scientific and technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

afficheront

-0.48

 Nhân

-0.45

karta

-0.45

ázquez

-0.42

Wul

-0.41

kna

-0.40

蔵

-0.39

 Krä

-0.39

erein

-0.38

keren

-0.38

POSITIVE LOGITS

ko

2.27

ko

2.04

Ko

2.03

Ko

1.92

KO

1.79

Co

1.70

Co

1.69

co

1.67

CO

1.59

CO

1.56

Activations Density 2.095%

words and terms related to "co" or "cooperation" concepts, including variations of the prefix "co" in scientific and technical contexts

No Comments

No Known Activations