INDEX

Explanations

terms related to risk factors and assessments in health and medical contexts

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

OGND

-0.62

 témoin

-0.58

adpleegd

-0.57

Edm

-0.57

rimid

-0.57

tonsoft

-0.54

ring

-0.54

 ring

-0.54

 بتاريخ

-0.51

ngdoc

-0.51

POSITIVE LOGITS

 factors

0.82

 posed

0.78

ier

0.75

 Factors

0.72

 factor

0.70

 profile

0.70

 assessment

0.69

 appetite

0.67

factors

0.67

 Profile

0.65

Activations Density 0.260%

terms related to risk factors and assessments in health and medical contexts

No Comments

No Known Activations