INDEX

Explanations

terms related to programming or technical terminologies, particularly those associated with object-oriented programming and accounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

AGA

-0.73

 McGovern

-0.71

 thence

-0.71

cotch

-0.71

licet

-0.70

GEBURTS

-0.69

 мол

-0.68

 Hawley

-0.68

期刊论文

-0.67

 Empires

-0.67

POSITIVE LOGITS

 Priya

0.97

 при

0.83

pri

0.81

 Przy

0.79

Bei

0.78

При

0.78

 При

0.78

 ddelweddau

0.77

Pry

0.76

Bij

0.75

Activations Density 0.176%

terms related to programming or technical terminologies, particularly those associated with object-oriented programming and accounts

No Comments

No Known Activations