INDEX

Explanations

combinations of verbs and adjectives indicating relationships

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

Following prepositions

np_acts-logits-general · gemini-2.0-flash

followed by prepositions

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 zoude

-0.45

Referințe

-0.40

 eneste

-0.39

 nowo

-0.38

 geest

-0.37

//

-0.37

 dezelve

-0.37

 entgeg

-0.37

 itulah

-0.36

 mijne

-0.35

POSITIVE LOGITS

 ब्रेकडाउन

0.57

 صوتيه

0.53

ContentLoaded

0.48

arakat

0.48

yelitis

0.46

Morfo

0.45

اعمال

0.44

PMailer

0.44

 noDo

0.42

principalColumn

0.42

Activations Density 0.789%

combinations of verbs and adjectives indicating relationships

Following prepositions

followed by prepositions

No Comments

No Known Activations