INDEX

Explanations

expressions related to programming functions and workflows

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

Variables/codes followed by symbols

np_acts-logits-general · gemini-2.0-flash

technical abbreviations and symbols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

 considérons

-0.36

 cant

-0.35

setof

-0.35

 سكانية

-0.35

 صوتيه

-0.34

匿名使用者

-0.32

 continúas

-0.32

↵

-0.32

なが

-0.31

Sat

-0.31

POSITIVE LOGITS

 Normdatei

0.74

StoryboardSegue

0.62

⟬

0.58

pulseira

0.55

imageshack

0.55

Autoritní

0.53

cartão

0.51

DataAnnotations

0.50

 betweenstory

0.50

iſen

0.49

Activations Density 1.187%

expressions related to programming functions and workflows

Variables/codes followed by symbols

technical abbreviations and symbols

No Comments

No Known Activations

expressions related to programming functions and workflows

Variables/codes followed by symbols

technical abbreviations and symbols

No Comments

No Known Activations