INDEX

Explanations

references to specific names and titles of works or authors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Migrations

-0.48

own

-0.47

“

-0.44

 consider

-0.43

}}=$

-0.43

obj

-0.43

vyt

-0.42

ant

-0.41

Eventually

-0.41

 eventually

-0.41

POSITIVE LOGITS

出版年

0.90

]")]

0.83

esModule

0.77

^(@)

0.76

 المعيارى

0.73

matchCondition

0.73

 JpaRepository

0.73

tvguidetime

0.71

 виправивши

0.71

 Italijanski

0.69

Activations Density 0.301%

references to specific names and titles of works or authors

No Comments

No Known Activations