INDEX

Explanations

terms related to specific medical conditions and treatment protocols

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

medical treatments

np_acts-logits-general · gemini-2.0-flash

standard and accepted treatment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

sociation

-0.44

 аппетита

-0.43

enterOuterAlt

-0.43

 esternos

-0.43

 recruiter

-0.43

 Peta

-0.41

 استنادى

-0.41

 StyleSheet

-0.41

ссы

-0.41

iertas

-0.40

POSITIVE LOGITS

 treatment

2.72

treatment

2.37

 Treatment

2.28

 treatments

2.22

Treatment

2.16

 TREATMENT

2.10

treat

1.97

 Treatments

1.91

 tratamiento

1.87

TREATMENT

1.85

Activations Density 0.954%

terms related to specific medical conditions and treatment protocols

medical treatments

standard and accepted treatment

No Comments

No Known Activations