INDEX

Explanations

words and phrases related to scientific analysis, ability, and the human condition

oai_token-act-pair · gemini-2.0-flash

terms related to data analysis and academic collaboration

np_token-act-pair-logits · gpt-4o-mini

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

kuuta

-0.56

Datuak

-0.53

patra

-0.49

ẵ

-0.46

ोध

-0.45

fty

-0.45

 الرياضيه

-0.44

Lähteet

-0.44

AddTagHelper

-0.43

 retrou

-0.43

POSITIVE LOGITS

 AssemblyProduct

0.71

complexContent

0.69

 PackageManager

0.68

出版年

0.67

XMLSchema

0.65

 BorderSide

0.63

 Superhosts

0.61

<",

0.60

 QtWidgets

0.59

WSGI

0.59

Activations Density 0.867%

words and phrases related to scientific analysis, ability, and the human condition

terms related to data analysis and academic collaboration

No Comments

No Known Activations