INDEX

Explanations

specific medical terms and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 للمعارف

-0.64

 nakalista

-0.60

msgTypes

-0.55

 betweenstory

-0.55

ChildScrollView

-0.54

 BoxDecoration

-0.52

queryInterface

-0.52

 onOptions

-0.51

 Италијани

-0.50

HideFlags

-0.50

POSITIVE LOGITS

Попис

0.38

GEBURTSDATUM

0.37

还好

0.35

heme

0.34

stery

0.33

rierten

0.33

otan

0.32

 tether

0.32

adamente

0.31

 régl

0.31

Activations Density 0.850%

specific medical terms and classifications

No Comments

No Known Activations