INDEX

Explanations

numeric data or mathematical expressions related to publications or academic references

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

出版年

-0.70

Geplaatst

-0.66

 يتيمه

-0.63

 uska

-0.63

 vuonna

-0.63

<bos>

-0.62

 beginnetje

-0.56

 出版

-0.54

 contextLoads

-0.53

嘧

-0.53

POSITIVE LOGITS

 betweenstory

0.74

adaptiveStyles

0.73

tvguidetime

0.58

 originaire

0.54

ViewInit

0.54

 LUMI

0.50

 snippetHide

0.49

Xaml

0.49

 विश्वसनीयता

0.48

alai

0.48

Activations Density 0.370%

numeric data or mathematical expressions related to publications or academic references

No Comments

No Known Activations