INDEX

Explanations

measurements and estimates related to precision and uncertainty in data analysis

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 financiero

-0.44

 miniaturka

-0.43

 mobilité

-0.42

 dorados

-0.42

 médicale

-0.42

 financieras

-0.42

 adquirido

-0.41

 Berlín

-0.41

 Jérusalem

-0.40

ſelf

-0.40

POSITIVE LOGITS

OCCURRED

0.52

-------------</

0.52

رشف

0.52

GEBURTSDATUM

0.52

bitField

0.49

scrapy

0.48

 nahilalakip

0.47

kew

0.45

postIndex

0.45

 autorytatywna

0.45

Activations Density 0.121%

measurements and estimates related to precision and uncertainty in data analysis

No Comments

No Known Activations