INDEX

Explanations

bibliographic references including publication details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 Отечественной

-0.63

互联网档案馆

-0.47

┬

-0.45

domésticos

-0.44

酌

-0.43

пиона

-0.43

github

-0.43

ίσ

-0.43

 awak

-0.42

 line

-0.42

POSITIVE LOGITS

 kasarigan

0.83

ValueStyle

0.79

 متعلقه

0.66

Notae

0.64

嘧

0.63

:✨

0.63

NameInMap

0.63

WireFormat

0.63

 Meksiku

0.61

товано

0.61

Activations Density 0.048%

bibliographic references including publication details

No Comments

No Known Activations