INDEX

Explanations

terms related to legal or regulatory documents and views

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

following prepositions from different languages

np_acts-logits-general · gemini-2.0-flash

mathematical and programming notation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

原始内容存档于

-0.59

Tó

-0.49

原始内容存档

-0.44

Den

-0.42

das

-0.41

couvrez

-0.41

FileUtils

-0.41

)))));

-0.41

FlowLayout

-0.40

TemporalType

-0.39

POSITIVE LOGITS

 Cæsar

0.89

 myſelf

0.88

 ſeveral

0.84

 againſt

0.83

 Monfieur

0.80

 Shakspeare

0.79

Efq

0.77

 purpoſe

0.76

 Conſ

0.75

 itſelf

0.74

Activations Density 0.041%

terms related to legal or regulatory documents and views

following prepositions from different languages

mathematical and programming notation

No Comments

No Known Activations