INDEX

Explanations

hexadecimal color codes and attributes in a coding context

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

numbers and symbols in code/styling

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 indígen

-0.48

 przecież

-0.47

Hozzáférés

-0.45

存于互联网档案馆

-0.43

 feroit

-0.43

 vectorielle

-0.42

rinfo

-0.42

carteles

-0.42

 contextLoads

-0.41

 obowią

-0.41

POSITIVE LOGITS

tanleria

0.45

windowFixed

0.44

 MenuView

0.39

 &___

0.39

-------

0.38

⤹

0.37

 AssemblyCulture

0.37

vician

0.36

enumii

0.35

 Umbra

0.34

Activations Density 0.010%

hexadecimal color codes and attributes in a coding context

numbers and symbols in code/styling

No Comments

No Known Activations