INDEX

Explanations

documentation and description of classes or methods in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

PreferredItem

-1.01

NameInMap

-0.96

 kaynağından

-0.95

parsedMessage

-0.92

 وتسجيلات

-0.89

IsContent

-0.87

ViewFeatures

-0.83

LookAnd

-0.82

ConstraintMaker

-0.78

CloseOperation

-0.77

POSITIVE LOGITS

for

0.53

 basic

0.50

 simple

0.50

ellular

0.49

 useful

0.49

 used

0.49

用于

0.49

出版年

0.47

basic

0.46

mith

0.45

Activations Density 0.334%

documentation and description of classes or methods in programming

No Comments

No Known Activations