INDEX

Explanations

various forms of numerical data, including counts, identifiers, and code snippets

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

下载附件

-0.59

fjspx

-0.58

BagLayout

-0.57

★★★★☆

-0.52

тости

-0.51

暂无

-0.51

XMLSchema

-0.50

 nonatomic

-0.50

обе

-0.50

JsonFormat

-0.49

POSITIVE LOGITS

 ExecuteAsync

0.62

énéral

0.56

!***

0.55

 imageNamed

0.54

 betweenstory

0.53

##

0.53

ViewImports

0.52

Zitat

0.51

 malades

0.50

berglass

0.50

Activations Density 1.666%

various forms of numerical data, including counts, identifiers, and code snippets

No Comments

No Known Activations