INDEX

Explanations

structured data formats, particularly relating to key-value pairs and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

FieldBuilder

-0.56

kwds

-0.55

ApiException

-0.54

中でも

-0.53

ronic

-0.53

InvalidProtocol

-0.52

Mutagenicity

-0.51

agian

-0.51

السكان

-0.50

Пото

-0.50

POSITIVE LOGITS

 autorytatywna

1.10

IntoConstraints

0.95

InputBorder

0.74

PositiveButton

0.58

</thead>

0.55

 Wicidata

0.52

Portail

0.52

Przeczytaj

0.48

NameInMap

0.47

 keten

0.47

Activations Density 0.484%

structured data formats, particularly relating to key-value pairs and syntax elements

No Comments

No Known Activations