INDEX

Explanations

phrases indicating the discovery or evidence of findings in research studies

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

found that

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

 يتيمه

-0.71

 незавершена

-0.60

">//

-0.60

 betweenstory

-0.58

 queſta

-0.57

🔰

-0.56

GK

-0.55

 OFDb

-0.54

 Equi

-0.54

 AssemblyTitle

-0.54

POSITIVE LOGITS

 encontraron

0.63

พบ

0.57

 found

0.56

 ditemukan

0.54

 encontró

0.50

發現

0.49

 Encuentra

0.48

 encontrou

0.48

 encontramos

0.48

 constater

0.48

Activations Density 0.068%

phrases indicating the discovery or evidence of findings in research studies

found that

No Comments

No Known Activations