INDEX

Explanations

technical and scientific terminology related to research and experimental methods

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

Text followed by "Q:"

np_acts-logits-general · gemini-2.0-flash

Mellana Apple Dementia Are

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

<eos>

-0.78

...

-0.54

...

-0.51

 которому

-0.50

JKLM

-0.50

youtu

-0.50

ciamo

-0.48

անգ

-0.48

 raison

-0.48

bės

-0.48

POSITIVE LOGITS

LookAnd

0.99

 kaarangay

0.80

 ſeveral

0.75

 myſelf

0.73

contentLoaded

0.73

 houſe

0.71

#+#

0.71

 ſever

0.70

 ſtate

0.69

下载附件

0.68

Activations Density 2.906%

technical and scientific terminology related to research and experimental methods

Text followed by "Q:"

Mellana Apple Dementia Are

No Comments

No Known Activations