INDEX

Explanations

names and proper nouns in diverse contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

acknowledgments and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 незавершена

-0.89

 للمعارف

-0.83

 мәкал

-0.82

 ویکی‌پدی

-0.82

 Chwiliwch

-0.80

 autorytatywna

-0.75

Rüyada

-0.75

 مرئيه

-0.75

WriteTagHelper

-0.74

GraphicsUnit

-0.73

POSITIVE LOGITS

0.40

</td>

0.35

0.34

0.32

0.31

 regalías

0.31

0.30

0.29

 Ambiental

0.29

Activations Density 0.034%

names and proper nouns in diverse contexts

acknowledgments and citations

No Known Activations