INDEX

Explanations

words or phrases associated with measurements and quantifications

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

endregion

-0.49

libft

-0.46

 Verder

-0.46

 gyhoeddwyd

-0.42

échal

-0.42

Билгалдахарш

-0.42

wau

-0.39

عرِّف

-0.39

 Babu

-0.39

 familières

-0.39

POSITIVE LOGITS

 ModelExpression

0.69

出版年

0.51

AnchorStyles

0.47

 CascadeType

0.46

ContentAsync

0.45

MLLoader

0.43

 quirúrg

0.42

 contactez

0.40

IBOutlet

0.39

HtmlAttribute

0.39

Activations Density 0.095%

words or phrases associated with measurements and quantifications

No Comments

No Known Activations