INDEX

Explanations

technical terms and concepts related to scientific analysis

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

detectable conditions and states

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

 diss

-0.27

 pointed

-0.25

 turned

-0.25

 TAMBIÉN

-0.25

Busy

-0.25

Ligações

-0.24

 setas

-0.24

ließlich

-0.24

 Sied

-0.24

her

-0.24

POSITIVE LOGITS

 ProtoMessage

0.80

 dAtA

0.79

 فريبيس

0.78

 <=",

0.73

المناصب

0.73

OGND

0.73

 يتيمه

0.68

出版年

0.67

 autorytatywna

0.66

ValueStyle

0.66

Activations Density 0.227%

technical terms and concepts related to scientific analysis

detectable conditions and states

No Comments

No Known Activations