INDEX

Explanations

names of authors and contributors in academic citations

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

author and title lines

np_acts-logits-general · gemini-2.5-flash-lite

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Diweddarwch

-0.59

+#+#

-0.59

irvana

-0.57

enetrable

-0.56

吋

-0.52

richTextPanel

-0.50

Попис

-0.49

XtraGrid

-0.48

 cakes

-0.46

ifikationer

-0.45

POSITIVE LOGITS

ագրություններ

0.48

 AttributeSet

0.37

脚注の使い方

0.36

 partnered

0.35

 partner

0.35

Бележки

0.34

 einges

0.33

assertSame

0.33

StringCopy

0.33

 SPDX

0.32

Activations Density 0.093%

names of authors and contributors in academic citations

author and title lines

No Comments

No Known Activations