INDEX

Explanations

phrases related to programming and technology

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

Followed by a question word or preposition

np_acts-logits-general · gemini-2.0-flash

introductory phrases

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

 itſelf

-0.93

berdayakan

-0.93

 whoſe

-0.89

 myſelf

-0.89

 mijne

-0.89

 themſelves

-0.86

 Monfieur

-0.86

 wikipagina

-0.85

 Anſ

-0.85

 nahilalakip

-0.84

POSITIVE LOGITS

„

0.92

 ressources

0.83

(=

0.82

 („

0.78

 nowadays

0.77

´

0.77

„

0.76

 Nowadays

0.74

Nr

0.71

 adresses

0.71

Activations Density 3.999%

phrases related to programming and technology

Followed by a question word or preposition

introductory phrases

No Comments

No Known Activations