INDEX

Explanations

words and terms associated with scientific models and variables

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

 Biôgrafia

-0.42

UAGES

-0.42

abestanden

-0.36

Gambas

-0.36

UseVisualStyle

-0.34

verwijspagina

-0.34

 beginnetje

-0.31

.*")]

-0.31

Gilla

-0.30

ragalactic

-0.30

POSITIVE LOGITS

 indígen

0.58

 kasarigan

0.57

HomeAsUpEnabled

0.50

ⓧ

0.49

woch

0.48

AccessorTable

0.48

UnknownFieldSet

0.47

StoryboardSegue

0.46

 plead

0.46

CloseOperation

0.45

Activations Density 1.661%

words and terms associated with scientific models and variables

No Comments

No Known Activations