INDEX

Explanations

terminology and concepts related to feature selection and descriptors in data analysis and machine learning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

Hochspringen

-0.64

DialogInterface

-0.52

ICOLON

-0.52

testng

-0.51

ătate

-0.51

SequentialGroup

-0.50

zino

-0.49

لكتر

-0.48

instancetype

-0.48

öhne

-0.48

POSITIVE LOGITS

atguigu

0.60

awtextra

0.58

 mxArray

0.57

RTEX

0.57

ьаж

0.54

 armband

0.53

TypedDataSet

0.52

 كمان

0.50

 prayers

0.50

TagHelper

0.50

Activations Density 0.354%

terminology and concepts related to feature selection and descriptors in data analysis and machine learning

No Comments

No Known Activations