INDEX

Explanations

terms related to medical conditions and healthcare scenarios

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

ſelf

-0.45

 Houſe

-0.45

NUMX

-0.44

 Afterward

-0.44

 auffi

-0.44

(;;)

-0.43

neſs

-0.43

 munitions

-0.42

 itſelf

-0.42

 nakalista

-0.41

POSITIVE LOGITS

GEBURTSDATUM

0.68

 Hence

0.66

 upto

0.62

 hence

0.59

 enquired

0.57

Hence

0.57

 India

0.54

riwal

0.54

 noOf

0.54

Numerology

0.54

Activations Density 1.630%

terms related to medical conditions and healthcare scenarios

No Comments

No Known Activations