INDEX

Explanations

references to specific quantities and classifications in scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.27.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

########.

-0.63

 disambiguazione

-0.61

#+#

-0.56

tvguidetime

-0.54

 Wiktionnaire

-0.51

<?

-0.50

 infierno

-0.49

-0.48

AutoModerator

-0.47

//

-0.45

POSITIVE LOGITS

الحياه

0.60

bibfield

0.44

fromnode

0.42

BibitemShut

0.40

HomeAsUp

0.40

fou

0.39

bibinfo

0.39

sor

0.38

 '\\;'

0.38

sor

0.38

Activations Density 0.710%

references to specific quantities and classifications in scientific research

No Comments

No Known Activations