INDEX

Explanations

technical terms and concepts related to data processing and Spark programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 väli

-0.35

ニュアル

-0.35

öz

-0.29

 posesión

-0.28

 sœur

-0.28

 pimienta

-0.27

 acresc

-0.27

 vedno

-0.26

 added

-0.26

姉妹

-0.26

POSITIVE LOGITS

hadoop

1.02

preduce

1.00

flink

0.94

mapreduce

0.91

 Hadoop

0.73

 snippetHide

0.73

 مشين

0.67

posedge

0.67

 Infórmanos

0.66

RectangleBorder

0.66

Activations Density 0.235%

technical terms and concepts related to data processing and Spark programming

No Comments

No Known Activations