INDEX

Explanations

patterns related to numerical data and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 '\\;'

-0.54

ModelForm

-0.51

 Normdatei

-0.51

UnusedPrivate

-0.50

 nonUne

-0.48

Chham

-0.48

uxxxx

-0.48

FXML

-0.47

MockBean

-0.47

windowFixed

-0.46

POSITIVE LOGITS

 vectorielle

0.51

Архівовано

0.47

 automatiques

0.43

 kasarigan

0.42

 groei

0.41

 ainfi

0.41

 grecque

0.40

 émotion

0.40

 slaap

0.40

 huden

0.40

Activations Density 0.586%

patterns related to numerical data and citations

No Comments

No Known Activations