INDEX

Explanations

references to measurements or numerical values in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

-0.66

 nonatomic

-0.49

０

-0.48

von

-0.46

蚪

-0.45

 mẽ

-0.44

niest

-0.42

Loh

-0.42

EndInit

-0.42

ngdoc

-0.42

POSITIVE LOGITS

 كومونز

0.80

 ambassade

0.79

 quæ

0.77

ValueStyle

0.74

 becauſe

0.72

 itſelf

0.72

 CHAPITRE

0.71

ADELPHIA

0.71

ENEFITS

0.70

 Venezia

0.70

Activations Density 0.553%

references to measurements or numerical values in a scientific context

No Comments

No Known Activations