INDEX

Explanations

references to specific locations, communities, or health-related terms in various contexts

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

出版年

-0.73

MLLoader

-0.55

TestingModule

-0.52

hoeddwyd

-0.50

 المعيارى

-0.50

__(/*!

-0.49

$_(

-0.49

탤

-0.48

ciclop

-0.48

 ioutil

-0.48

POSITIVE LOGITS

 other

0.45

 lainnya

0.45

 Chwiliwch

0.43

 demás

0.40

+#+#

0.39

 demais

0.39

 diğer

0.38

以此

0.37

อื่น

0.36

createTextNode

0.36

Activations Density 0.133%

references to specific locations, communities, or health-related terms in various contexts

No Comments

No Known Activations