INDEX

Explanations

mathematical symbols and expressions related to linear transformations

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

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 resourceCulture

-0.55

CloseOperation

-0.53

esModule

-0.46

 himſelf

-0.44

tedly

-0.44

UnusedPrivate

-0.43

 myſelf

-0.42

setVerticalGroup

-0.41

migrationBuilder

-0.41

 Diſ

-0.41

POSITIVE LOGITS

 Italijani

0.41

 يتيمه

0.39

findung

0.39

InjectAttribute

0.38

creva

0.37

vantages

0.36

ebilir

0.36

 COMPET

0.35

 communiquez

0.35

 Насе

0.34

Activations Density 0.048%

mathematical symbols and expressions related to linear transformations

mathematical symbols and notation

No Comments

No Known Activations