INDEX

Explanations

references to books and stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

UserScript

-0.52

XmlSchema

-0.51

 Wikimedijinoj

-0.50

ruptedException

-0.46

 userSchema

-0.46

 Matri

-0.45

уме

-0.45

Strain

-0.45

liosis

-0.44

 comer

-0.44

POSITIVE LOGITS

ViewImports

0.68

 potuto

0.61

rungsseite

0.57

($__

0.57

MemoryWarning

0.57

InjectAttribute

0.56

esez

0.56

 مواليد

0.55

ⓧ

0.54

retario

0.54

Activations Density 0.279%

references to books and stories

No Comments

No Known Activations