INDEX

Explanations

phrases expressing opinions or judgments on appropriateness or desirability

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

Follows "be," "it," "of," "is," or "on."

np_acts-logits-general · gemini-2.0-flash

it would be

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

 متعلقه

-0.61

 يتيمه

-0.57

 arşivlendi

-0.54

 AssemblyVersion

-0.53

ChildScrollView

-0.48



-0.48

 فريبيس

-0.45

adaptiveStyles

-0.44

setDo

-0.44

󠁮

-0.43

POSITIVE LOGITS

 important

0.49

 gesteld

0.49

entibus

0.41

 dezelve

0.40

 zelve

0.40

!*\

0.38

 possible

0.38

 Ella

0.38

 aika

0.38

 wise

0.37

Activations Density 0.295%

phrases expressing opinions or judgments on appropriateness or desirability

Follows "be," "it," "of," "is," or "on."

it would be

No Comments

No Known Activations