INDEX

Explanations

occurrences of the term "com" related to programming or package namespaces

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 elsewhere

-0.53

 rappel

-0.52

 utilizarse

-0.52

 schne

-0.51

愈

-0.49

hitung

-0.48

 Langu

-0.46

 oublier

-0.46

 muchacha

-0.46

 lente

-0.46

POSITIVE LOGITS

com

2.99

Com

0.98

COM

0.93

org

0.84

发表于

0.80

con

0.80

InputBorder

0.72

 AssemblyTitle

0.71

edu

0.71

 comer

0.70

Activations Density 0.077%

occurrences of the term "com" related to programming or package namespaces

No Comments

No Known Activations