INDEX

Explanations

terms related to medical efficacy and patient characteristics

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

 AssemblyCulture

-0.47

 autorytatywna

-0.43

 Spisak

-0.40

 navideño

-0.40

hysema

-0.39



-0.39

 său

-0.39

 nahilalakip

-0.38

ScopeManager

-0.37

 unknownFields

-0.37

POSITIVE LOGITS

SequentialGroup

0.54

 otomatig

0.49

tonode

0.48

bootstrapcdn

0.47

EndInit

0.42

EndGlobalSection

0.41

PyExc

0.41

phazard

0.41

TK

0.41

 CART

0.40

Activations Density 1.066%

terms related to medical efficacy and patient characteristics

No Comments

No Known Activations