INDEX

Explanations

XML-related tags and attributes

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

KURZBESCHREIBUNG

-0.49



-0.47

bootstrapcdn

-0.47

principalTable

-0.46

InputBorder

-0.46

 venganza

-0.46

sizeCache

-0.46

HandlerContext

-0.45

 >=",

-0.44

 betweenstory

-0.43

POSITIVE LOGITS

 tartalomajánló

0.51

orec

0.50

 nahilalakip

0.48

 RISERVATA

0.46

 Autorisations

0.46

tangentMode

0.45

 valu

0.42

inkscape

0.42

Expanded

0.41

ValueStyle

0.40

Activations Density 1.064%

XML-related tags and attributes

No Comments

No Known Activations