INDEX

Explanations

a variety of words, some of which are related to compilers, some to personality traits, some to holidays, others to judicial nominees, and others with less obvious relationships.

oai_token-act-pair · gemini-2.0-flash

Networking and fiction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EXT

-0.40

fun

-0.39

explo

-0.38

)))),

-0.37

hot

-0.37

ata

-0.36

dig

-0.36

 millions

-0.36

tec

-0.36

osa

-0.36

POSITIVE LOGITS

verwijspagina

0.78

 виправивши

0.73

 financière

0.67

MLLoader

0.63

 stället

0.62

 provisoire

0.61

AndroidJUnit

0.60

 Theſe

0.60

 BoxFit

0.60

makeConstraints

0.60

Activations Density 2.964%

a variety of words, some of which are related to compilers, some to personality traits, some to holidays, others to judicial nominees, and others with less obvious relationships.

Networking and fiction

No Comments

No Known Activations

a variety of words, some of which are related to compilers, some to personality traits, some to holidays, others to judicial nominees, and others with less obvious relationships.

Networking and fiction

No Comments

No Known Activations