INDEX

Explanations

medical and biochemical terminology related to specific assays or experimental results

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

batore

-0.62

 playmobil

-0.55

ctez

-0.54

BagLayout

-0.53

 saveiro

-0.52

Datuak

-0.51

Siege

-0.49

 émer

-0.49

tlement

-0.48

hearsed

-0.48

POSITIVE LOGITS

expandindo

0.51

المكان

0.40

 препратки

0.39

IndentedString

0.39

TagMode

0.36

AutoField

0.35

disposing

0.33

uertos

0.32

RRect

0.32

ApiOperation

0.32

Activations Density 1.212%

medical and biochemical terminology related to specific assays or experimental results

No Comments

No Known Activations