INDEX

Explanations

references to the structure and organization of a research paper or academic work

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 ब्रेकडाउन

-0.76

ロウィン

-0.66

 الحره

-0.65

niſſe

-0.63

iſen

-0.62

iſchen

-0.62

ſſung

-0.60

ſcher

-0.59

Ӕ

-0.58

IUrlHelper

-0.58

POSITIVE LOGITS

 EClass

0.40

......

0.35

føl

0.33

...

0.33

...,

0.32

..."

0.31

..

0.31

.........

0.31

 Dumnezeu

0.30

Soon

0.30

Activations Density 1.708%

references to the structure and organization of a research paper or academic work

No Comments

No Known Activations