INDEX

Explanations

titles and references to published works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 فريبيس

-0.80

 setempat

-0.67

ReusableCell

-0.65

=$?

-0.65

الحياه

-0.64

NameInMap

-0.63

 GetEnumerator

-0.62

bkz

-0.61

Obrázky

-0.61

++

-0.61

POSITIVE LOGITS

#+#

0.52

which

0.47

 presentado

0.44

 starring

0.44

TM

0.44

میز

0.44

 which

0.43

 featuring

0.42

 fotogra

0.42

 नाम

0.41

Activations Density 0.409%

titles and references to published works

No Comments

No Known Activations