INDEX

Explanations

references to articles created by bots

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

references and citations

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

-0.37

עה

-0.37

 Koch

-0.37

 inside

-0.36

ola

-0.36

anlagen

-0.35

 Bestand

-0.35

 maat

-0.35

 atsi

-0.34

an

-0.34

POSITIVE LOGITS

 ویکی‌پدی

1.33

 Roskov

1.09

تقاوى

1.05

tagHelperRunner

0.97

 Мексичка

0.96

ंदीखरीदारी

0.95

 мәкал

0.94

 pinulongan

0.93

Autoritní

0.91

 Signalez

0.88

Activations Density 0.084%

references to articles created by bots

references and citations

No Comments

No Known Activations