INDEX

Explanations

phrases related to ongoing projects or tasks

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

"working on"

np_acts-logits-general · gemini-2.0-flash

working on projects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

mybatisplus

-0.50

 vectorielle

-0.45

 calendriers

-0.43

rawDesc

-0.43

 popolari

-0.43

glyphicon

-0.42

 AssemblyCompany

-0.42

WireFormatLite

-0.42

 HasFactory

-0.41

 Réponses

-0.41

POSITIVE LOGITS

 Project

0.60

working

0.58

Project

0.55

 작업

0.54

Working

0.54

 working

0.53

fix

0.53

 bearbeitet

0.52

Worked

0.52

 Work

0.51

Activations Density 0.163%

phrases related to ongoing projects or tasks

"working on"

working on projects

No Comments

No Known Activations