INDEX

Explanations

references to formal processes, procedures, and verification in an official context

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Followed by percentages or quantities

np_acts-logits-general · gemini-2.0-flash

quantities and time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

Negative Logits

>--}}

-0.67

 nonUne

-0.54

 թվական

-0.54

тьяна

-0.52

 pinulongan

-0.51

 onAnimation

-0.50

são

-0.49

 مُعرِّف

-0.48

知的

-0.48

 Claudius

-0.45

POSITIVE LOGITS

URLException

0.64

 Paglinawan

0.57

anyahu

0.56

AccessorTable

0.56

niająca

0.56

queryInterface

0.53

rizona

0.52

 ultimate

0.51

copg

0.51

kels

0.50

Activations Density 0.115%

references to formal processes, procedures, and verification in an official context

Followed by percentages or quantities

quantities and time periods

No Known Activations