INDEX

Explanations

references to the XS programming interface or framework

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

Japanese polite endings and 'xs'/'obs'

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

 Maitland

-0.48

MLLoader

-0.47

ⓧ

-0.47

subpackage

-0.47

Slf

-0.46

meliharaan

-0.45

 LOGGER

-0.44

Itoa

-0.44

ситет

-0.44

 Lein

-0.43

POSITIVE LOGITS

xs

1.45

xs

1.30

XS

1.19

XS

1.16

Xs

0.91

Xs

0.86

0.69

bs

0.65

zs

0.65

YS

0.61

Activations Density 0.004%

references to the XS programming interface or framework

Japanese polite endings and 'xs'/'obs'

No Comments

No Known Activations