INDEX

Explanations

numerical values, possibly related to measurements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

iste

-0.42

 Sewell

-0.37

宮

-0.35

 insectos

-0.35

udur

-0.35

Насе

-0.34

 interpretación

-0.34

 ChromeDriver

-0.33

 dritten

-0.33

mon

-0.33

POSITIVE LOGITS

SourceChecksum

0.93

 يتيمه

0.93

ValueStyle

0.92

RegressionTest

0.89

UnusedPrivate

0.89

oredCriteria

0.88

WireFormatLite

0.86

TypedDataSet

0.85

ьаж

0.82

 Мексичка

0.81

Activations Density 0.652%

numerical values, possibly related to measurements or statistics

No Comments

No Known Activations