INDEX

Explanations

terms related to pain management and treatment options

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

preceding medical treatments

np_acts-logits-general · gemini-2.0-flash

medical treatments and therapies

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

 facie

-0.61

 unknownFields

-0.49

Fatalf

-0.49

 Dundas

-0.47

getActiveSheet

-0.47

ParseException

-0.46

Viited

-0.46

Malformed

-0.44

cipar

-0.44

diğinde

-0.44

POSITIVE LOGITS

 medication

1.15

 medications

1.04

 supplements

0.97

 drugs

0.95

 antidepressants

0.95

medication

0.94

 meds

0.94

 diet

0.93

 medicines

0.93

Medication

0.91

Activations Density 0.785%

terms related to pain management and treatment options

preceding medical treatments

medical treatments and therapies

No Comments

No Known Activations