INDEX

Explanations

structured data related to various scientific and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

initializeApp

-0.48

vs

-0.44

HasOne

-0.41

事

-0.41

inz

-0.41

 privil

-0.40

 visiter

-0.40

 сча

-0.39

fa

-0.39

POSITIVE LOGITS

ंदीखरीदारी

0.85

oa̍t

0.83

 otomatig

0.73

]<<"

0.70

ſelves

0.70

 Theſe

0.69

 فريبيس

0.69

Personensuche

0.68

ſelf

0.68

findpost

0.68

Activations Density 0.117%

structured data related to various scientific and technical terms

No Comments

No Known Activations