INDEX

Explanations

concepts related to personal growth and community engagement

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

articles and descriptive phrases

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

Not in Any Lists

No Comments

Negative Logits

ANTLR

-0.41

IANA

-0.38

lati

-0.36

 Haji

-0.36

󠁣

-0.36

ynes

-0.36

vra

-0.35

dis

-0.35

lan

-0.35

 חיצוניים

-0.35

POSITIVE LOGITS

 ویکی‌پدی

0.72

 désolés

0.55

 سكانية

0.55

 للاسماء

0.54

 betweenstory

0.52

 itſelf

0.52

ScopeManager

0.51

 myſelf

0.51

 raiſ

0.49

gameserver

0.48

Activations Density 0.054%

concepts related to personal growth and community engagement

articles and descriptive phrases

No Comments

No Known Activations