INDEX

Explanations

terms related to health and medical conditions, specifically those affecting kidney function

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

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

contextualized prepositions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

<bos>

-0.74

Vidite

-0.71

 ostensibly

-0.67

 decidedly

-0.67

Conversely

-0.62

vermectin

-0.62

 whence

-0.60

FWIW

-0.60

 Conversely

-0.59

Essentially

-0.58

POSITIVE LOGITS

 different

0.95

 researches

0.88

few

0.86

 equipments

0.83

 evidences

0.82

different

0.81

 différent

0.75

 Different

0.74

 متعلقه

0.72

 advices

0.72

Activations Density 1.249%

terms related to health and medical conditions, specifically those affecting kidney function

followed by prepositions

contextualized prepositions

No Comments

No Known Activations