INDEX

Explanations

instances of numerical or statistical data in the document

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

featureID

-0.91

EDEFAULT

-0.90

Hentet

-0.86

HasAnnotation

-0.85

ArrowToggle

-0.83

AndEndTag

-0.83

ValueStyle

-0.83

WebVitals

-0.82

PreferredItem

-0.79

RTLD

-0.79

POSITIVE LOGITS

readAs

0.48

toUpperCase

0.47

Rüyada

0.47

 Autorizaciones

0.44

 Reporting

0.43

0.42

0.41

\\

0.41

strncpy

0.40

 reporting

0.40

Activations Density 0.205%

instances of numerical or statistical data in the document

No Comments

No Known Activations