INDEX

Explanations

HTML tags and structure within the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 فريبيس

-0.80

 gynhyrchwyd

-0.71

########.

-0.71

 estekak

-0.67

Datuak

-0.65

omitempty

-0.64

enumi

-0.64

 Italijanski

-0.60

دانشنامهٔ

-0.60

bootstrapcdn

-0.59

POSITIVE LOGITS

SharedCtor

0.50

<bos>

0.45

 style

0.44

 Schriftsteller

0.42

MemoryWarning

0.42

 AssemblyCompany

0.41

 чего

0.41

 Thrones

0.40

corazón

0.40

ouwen

0.40

Activations Density 0.080%

HTML tags and structure within the document

No Comments

No Known Activations