INDEX

Explanations

mathematical notation and expressions related to eigenvalues and eigenvectors

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

Math formulas or expressions

np_acts-logits-general · gemini-2.0-flash

mathematical notation or code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 original

-0.57

sizeCache

-0.51

 VIDEOTAPE

-0.50

verdad

-0.49

original

-0.49

NewRow

-0.48

ItemBackground

-0.48

GOTREF

-0.47

 onItemClick

-0.47

HideFlags

-0.47

POSITIVE LOGITS

="@+

0.61

ніципалі

0.58

unft

0.58

 universitaria

0.57

DockStyle

0.56

 aikaa

0.53

 Acerca

0.53

 Previously

0.53

 étoit

0.53

 renfer

0.52

Activations Density 0.223%

mathematical notation and expressions related to eigenvalues and eigenvectors

Math formulas or expressions

mathematical notation or code

No Comments

No Known Activations