INDEX

Explanations

references to specific authors and their works within scientific discussions

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sicherung

-0.54

 hallaz

-0.48

 nuestras

-0.48

 McAllister

-0.47

 Wohnen

-0.47

 Architektur

-0.47

tructuring

-0.46

 Findlay

-0.45

 Erziehung

-0.45

 inmueble

-0.45

POSITIVE LOGITS

quelize

0.68

erializer

0.65

Hawks

0.63

Cep

0.62

TSR

0.60

 sympy

0.60

CTS

0.60

 Phaser

0.60

 Hawks

0.59

CID

0.58

Activations Density 1.670%

references to specific authors and their works within scientific discussions

No Comments

No Known Activations