INDEX

Explanations

present tense verbs related to finding and adjusting personal preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Paglinawan

-0.72

 BoxFit

-0.67

ChildScrollView

-0.67

期刊论文

-0.65

Diwedd

-0.64

GIVEREF

-0.63

 Италијани

-0.63

 Extragalactic

-0.63

 podjela

-0.62

__":

-0.60

POSITIVE LOGITS

 personally

0.61

 prefer

0.58

 personal

0.53

Personally

0.52

preferences

0.51

 Personally

0.51

 prefi

0.51

 persönlich

0.50

 personale

0.47

 pribadi

0.47

Activations Density 0.334%

present tense verbs related to finding and adjusting personal preferences

No Comments

No Known Activations