INDEX

Explanations

terms related to the "Tro" prefix, possibly focused on types of assays, infections, or classifications associated with a specific context

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

"Tro" followed by other letters

np_acts-logits-general · gemini-2.0-flash

words starting with Tro

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SwitchCompat

-0.51

 getItemId

-0.42

 composés

-0.41

 CURIAM

-0.39

 sintética

-0.38

kuuta

-0.38

 compuestos

-0.37

 telefónica

-0.37

 múltiple

-0.37

Spiel

-0.37

POSITIVE LOGITS

tro

0.64

Tro

0.63

Tro

0.61

tro

0.58

SourceChecksum

0.56

TRO

0.52

 nahilalakip

0.50

Aro

0.47

TRO

0.46

DataSnapshot

0.46

Activations Density 0.285%

terms related to the "Tro" prefix, possibly focused on types of assays, infections, or classifications associated with a specific context

"Tro" followed by other letters

words starting with Tro

No Comments

No Known Activations