INDEX

Explanations

information related to health conditions and their implications

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

Preceding specific words or phrases

np_acts-logits-general · gemini-2.0-flash

details required

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

*~*~

-0.49

 Merlot

-0.49

 ་་

-0.47

 ferret

-0.47

()',

-0.44

',

-0.44

,’”

-0.44

 Outlaw

-0.44

()")

-0.43

?“

-0.43

POSITIVE LOGITS

 equipments

0.78

 Nowadays

0.67

 firstly

0.67

 informations

0.63

 advices

0.62

Nowadays

0.60

 nowadays

0.60

 convenable

0.59

LookAnd

0.58

 appunto

0.58

Activations Density 4.078%

information related to health conditions and their implications

Preceding specific words or phrases

details required

No Comments

No Known Activations