INDEX

Explanations

references to technical topics or specific programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

ьаж

-0.78

ForValue

-0.65

 سكانية

-0.56

RTLD

-0.53

encodeWith

-0.52

addCriterion

-0.52

 PyLong

-0.50

resave

-0.50

 informée

-0.50

érées

-0.50

POSITIVE LOGITS

 становника

0.69

stdafx

0.63

出版年

0.62

findpost

0.59

?>">

0.54

SequentialGroup

0.54

/**

0.50

RenderAtEndOf

0.49

MethodManager

0.49

 palms

0.49

Activations Density 1.397%

references to technical topics or specific programming concepts

No Comments

No Known Activations