INDEX

Explanations

terms related to medical symptoms and patient conditions

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

 kasarigan

-0.61

 nakalista

-0.60

 Administrativna

-0.57

 gyhoeddwyd

-0.55

 <>",

-0.53

 utafitiHapana

-0.52

IntoConstraints

-0.52

ագրություններ

-0.52

AccessorTable

-0.50

 kohdetta

-0.50

POSITIVE LOGITS

ValueStyle

0.44

wantErr

0.40

fromnode

0.37

fetchone

0.35

Manbalar

0.34

Vanjske

0.32

RUnlock

0.32

">//

0.31

øv

0.31

envolvimento

0.31

Activations Density 0.055%

terms related to medical symptoms and patient conditions

No Comments

No Known Activations