INDEX

Explanations

mentions of medical interventions and evaluations concerning patient care

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

 Nowadays

-0.90

Nowadays

-0.84

 nowadays

-0.82

 equipments

-0.66

 policemen

-0.65

いろいろな

-0.65

 everybody

-0.63

 advices

-0.63

 marvellous

-0.62

 tadi

-0.61

POSITIVE LOGITS

)";

0.89

 pleaſure

0.85

 incentiv

0.85

SEGUIR

0.84

 transitioning

0.83

 comedic

0.83

sedown

0.83

 Majefty

0.82

 transitioned

0.81

Ծանոթ

0.81

Activations Density 1.208%

mentions of medical interventions and evaluations concerning patient care

No Comments

No Known Activations