INDEX

Explanations

phrases related to risk factors and health outcomes associated with medical conditions

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

Increased risk or risk factors

np_acts-logits-general · gemini-2.0-flash

at high risk

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

writeFieldEnd

-0.69

matchCondition

-0.66

omock

-0.59

Демографія

-0.55

setopt

-0.53

 AssemblyVersion

-0.48

 nahilalakip

-0.47

 TType

-0.47

 finais

-0.47

setScene

-0.46

POSITIVE LOGITS

 risk

2.02

 Risk

1.76

risk

1.72

Risk

1.65

 risks

1.59

 RISK

1.57

 riesgo

1.46

RISK

1.39

 risque

1.37

 Risks

1.37

Activations Density 0.730%

phrases related to risk factors and health outcomes associated with medical conditions

Increased risk or risk factors

at high risk

No Comments

No Known Activations