INDEX

Explanations

references to technical commands or programming syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\{\\

-0.70

 calendriers

-0.66

出版年

-0.58

]));

-0.56

 jspb

-0.56

 IBRARY

-0.55

LabelTagHelper

-0.55

 '\\;'

-0.54

 EconPapers

-0.54

']);

-0.53

POSITIVE LOGITS

 سكانية

0.53

arko

0.48

modi

0.47

 الرخصة

0.46

MemoryWarning

0.45

下载附件

0.44

mitted

0.44

 esboço

0.43

Qed

0.43

offsetWidth

0.43

Activations Density 0.598%

references to technical commands or programming syntax

No Comments

No Known Activations