INDEX

Explanations

terms related to statistical analyses and medical risk factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ChildScrollView

-0.71

inerja

-0.59

JspWriter

-0.53

 Waray

-0.53

 oprot

-0.52

weile

-0.52

BorderFactory

-0.52

kmäler

-0.51

idopsis

-0.51

ษัท

-0.51

POSITIVE LOGITS

 odds

0.79

 hazard

0.77

 adjusted

0.75

 Odds

0.73

 للاسماء

0.71

Odds

0.70

hazard

0.69

 Hazard

0.66

OR

0.66

OR

0.65

Activations Density 3.003%

terms related to statistical analyses and medical risk factors

No Comments

No Known Activations