INDEX

Explanations

terms related to spinal cord injuries and their medical implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 TestBed

-0.43

seido

-0.42

 faltan

-0.41

TargetException

-0.41

naie

-0.41

ktır

-0.40

 enfrent

-0.40

idable

-0.40

DECREF

-0.39

Rohy

-0.39

POSITIVE LOGITS

 spinal

0.62

 Spinal

0.60

 Spine

0.57

spinal

0.52

 nerv

0.52

 Neurol

0.50

 Nervous

0.49

 nerve

0.49

 Neurology

0.49

 Nerve

0.49

Activations Density 0.388%

terms related to spinal cord injuries and their medical implications

No Comments

No Known Activations