INDEX

Explanations

references to matrices and their properties

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

the word "matrix"

np_acts-logits-general · gemini-2.0-flash

mathematical matrix context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

getOriginal

-0.46

Good

-0.34

Goodnight

-0.33

wyn

-0.33

 Gust

-0.32

Protected

-0.32

!).

-0.32

CPL

-0.32

 Discover

-0.32

symp

-0.31

POSITIVE LOGITS

 matrix

2.66

matrix

2.47

 Matrix

2.45

Matrix

2.33

 MATRIX

2.27

 matrices

2.06

 Matrices

1.95

MATRIX

1.92

 matriz

1.85

矩阵

1.84

Activations Density 0.163%

references to matrices and their properties

the word "matrix"

mathematical matrix context

No Comments

No Known Activations