INDEX

Explanations

references to official meetings and sessions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

Personendaten

-0.70

 ujednoznacz

-0.60

 disambiguazione

-0.58

 فريبيس

-0.56

makeText

-0.54

tagHelperRunner

-0.53

MemoryWarning

-0.52

makeConstraints

-0.50

 <<<<<<<<<<<<<<

-0.48

IsContent

-0.48

POSITIVE LOGITS

 Lingkungan

0.53

 adjourned

0.48

 attendance

0.47

 adjour

0.44

 seconded

0.43

 excused

0.43

 Keuangan

0.43

 minutes

0.43

 Chairperson

0.42

 yapılan

0.42

Activations Density 0.246%

references to official meetings and sessions

No Comments

No Known Activations