INDEX

Explanations

phrases indicating changes or transformations in states or conditions

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

PCR DNA

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

PX

-0.49

 relâche

-0.42

adpleegd

-0.42

DrawerToggle

-0.40

ⓧ

-0.39

YYY

-0.38

putnik

-0.35

fazione

-0.35

تب

-0.34

TCM

-0.34

POSITIVE LOGITS

RenderAtEndOf

0.54

 NDEBUG

0.47

Demografie

0.46

inSlope

0.46

Personendaten

0.44

mybatisplus

0.42

HtmlAttribute

0.42

PMailer

0.42

 BoxDecoration

0.41

loride

0.40

Activations Density 0.065%

phrases indicating changes or transformations in states or conditions

PCR DNA

No Comments

No Known Activations