INDEX

Explanations

specific technical terms and jargon related to software, health, and regulatory contexts

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

/**

-0.60

VYMaps

-0.60

ⓧ

-0.59

 صوتيه

-0.58

 surla

-0.57

SourceChecksum

-0.57

 nonUne

-0.53

AccessorTable

-0.53

 kaarangay

-0.52

Geplaatst

-0.51

POSITIVE LOGITS

 XNUMX

0.50

 affari

0.37

 ucapnya

0.35

NUMX

0.34

 tournée

0.33

 précédentes

0.33

 vítimas

0.32

 sepol

0.32

 Utilizamos

0.32

ItemGroup

0.31

Activations Density 0.085%

specific technical terms and jargon related to software, health, and regulatory contexts

No Comments

No Known Activations