INDEX

Explanations

special characters and formatting elements used in coding or markup languages

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

Code and configuration file fragments

np_acts-logits-general · gemini-2.0-flash

XML configuration snippets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 rhythm

-0.68

UserScript

-0.63

 momentum

-0.59

 ritmo

-0.57

 speed

-0.56

invokeLater

-0.55

rhythm

-0.52

ilibrium

-0.52

momentum

-0.50

 equilibrium

-0.49

POSITIVE LOGITS

 يتيمه

0.57

enumii

0.54

}${

0.53

präche

0.53

enumi

0.52

 mesas

0.50

unknownFields

0.50

</tfoot>

0.49

 otomatig

0.47

ApiModelProperty

0.47

Activations Density 0.236%

special characters and formatting elements used in coding or markup languages

Code and configuration file fragments

XML configuration snippets

No Comments

No Known Activations