INDEX

Explanations

statistical terms and concepts related to analysis and regression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Mag

-0.45

viewDidLoad

-0.42

Ծանոթ

-0.41

go

-0.40

mag

-0.39

 maximum

-0.38

stretchr

-0.38

Mag

-0.37

Ne

-0.37

POSITIVE LOGITS

+#+#

1.03

 pinulongan

1.00

 AssemblyCulture

0.96

 propOrder

0.92

LookAnd

0.90

 nahilalakip

0.89

Personendaten

0.89

findpost

0.89

 Winaray

0.87

aarrggbb

0.86

Activations Density 0.672%

statistical terms and concepts related to analysis and regression

No Comments

No Known Activations