INDEX

Explanations

structured data or key-value pairs, likely in the context of programming or databases

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

Code or version-related information

np_acts-logits-general · gemini-2.0-flash

administrative center

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

 affitto

-0.54

 authentique

-0.51

 fièvre

-0.46

 cittadini

-0.46

 valable

-0.46

 recente

-0.46

 silvestre

-0.45

 hacerlo

-0.45

SYNOPSIS

-0.45

 choisis

-0.45

POSITIVE LOGITS

ReusableCell

0.84

 متعلقه

0.81

WebVitals

0.76

')")

0.71

Identyfik

0.70

)";

0.69

:][

0.69

'])->

0.69

'):

0.68

Enllaces

0.67

Activations Density 0.125%

structured data or key-value pairs, likely in the context of programming or databases

Code or version-related information

administrative center

No Comments

No Known Activations