INDEX

Explanations

mentions of notable television news programs and news networks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

enderror

-0.63

 wikipagina

-0.59

 iconLine

-0.51

 Wikiseite

-0.50

 tartalomajánló

-0.50

hyrchwyd

-0.48

IntoConstraints

-0.47

ValueStyle

-0.43

 referrerpolicy

-0.43

 Мексичка

-0.43

POSITIVE LOGITS

 likewise

0.51

NullCheck

0.45

ContentLoaded

0.45

 similarly

0.42

 also

0.41

 ويكيميديا

0.41

 тоже

0.39

 szint

0.38

 Speck

0.37

}}^{

0.36

Activations Density 1.158%

mentions of notable television news programs and news networks

No Comments

No Known Activations