INDEX

Explanations

medical terms related to stroke and oxygen treatment

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

strokes and neurology

np_acts-logits-general · gemini-2.0-flash

neurological stroke

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 PTFE

-0.68

Omn

-0.61

 bellows

-0.61

 feen

-0.59

 carab

-0.58

 nephe

-0.57

 JpaRepository

-0.57

 Swarovski

-0.55

Apparel

-0.55

 boilers

-0.55

POSITIVE LOGITS

 neuro

1.19

 brain

1.04

 Brain

1.02

 Neuro

1.01

 Neuros

0.99

Neuro

0.97

 neurological

0.96

 Neurol

0.96

neuro

0.94

 Neurological

0.92

Activations Density 0.855%

medical terms related to stroke and oxygen treatment

strokes and neurology

neurological stroke

No Comments

No Known Activations