INDEX

Explanations

mathematical symbols and notations

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

$\mathrm{Tr}$ or `rm` in math/code

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

 Obrador

-0.41

Fatalf

-0.33

hört

-0.32

 cref

-0.31

imread

-0.30

obs

-0.30

发表于

-0.30

leqq

-0.29

 estekak

-0.28

tangentMode

-0.28

POSITIVE LOGITS

RenderAtEndOf

0.53

alakip

0.52

essentiel

0.51

 pouvoit

0.50

 avoient

0.50

ंदीखरीदारी

0.50

ulongan

0.50

 wiſſen

0.50

ロウィン

0.49

erintah

0.49

Activations Density 0.257%

mathematical symbols and notations

$\mathrm{Tr}$ or `rm` in math/code

No Comments

No Known Activations