INDEX

Explanations

references to brands and their products within context

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

<start_of_turn> user

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

 ویکی‌پدی

-0.60

الحياه

-0.48

 INTERESAR

-0.45

Datuak

-0.44

EndGlobalSection

-0.43

fjspx

-0.42

 Biôgrafia

-0.42

dafx

-0.42

SBATCH

-0.41

 Italijanski

-0.41

POSITIVE LOGITS

setVerticalGroup

0.44

 północ

0.42

Према

0.40

verd

0.40

AnchorStyles

0.39

 uitz

0.38

candidate

0.37

 Gallardo

0.37

delning

0.37

 directora

0.37

Activations Density 0.019%

references to brands and their products within context

<start_of_turn> user

No Comments

No Known Activations