INDEX

Explanations

phrases and terminology that describe mathematical relationships and dependencies in a scientific context

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

a function of

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

UnusedPrivate

-0.44

enterOuterAlt

-0.41

saraba

-0.36

-0.33

fore

-0.31

FT

-0.31

 conducted

-0.30

FL

-0.30

 talking

-0.29

Qu

-0.29

POSITIVE LOGITS

$_(

0.75

 يتيمه

0.73

 Infórmanos

0.73

verwijspagina

0.70

Portale

0.69

$_"

0.69

 pinulongan

0.67

 transfieras

0.66

HasIndex

0.65

 ainfi

0.65

Activations Density 0.323%

phrases and terminology that describe mathematical relationships and dependencies in a scientific context

a function of

No Comments

No Known Activations