INDEX

Explanations

technical terms and structures related to email headers and configurations

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

Newline characters and related errors

np_acts-logits-general · gemini-2.0-flash

newline, carriage return, endl

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

出版年

-0.56

پیوند

-0.53

iredo

-0.53

Geplaatst

-0.52

 primaria

-0.51

 aimer

-0.50

хь

-0.49

 tweezers

-0.49

 auprès

-0.47

ValueMap

-0.47

POSITIVE LOGITS

"\

0.93

 newline

0.83

'\

0.80

newLine

0.79

,"\

0.79

"\

0.76

","\

0.75

 endl

0.74

("\

0.74

newline

0.73

Activations Density 0.222%

technical terms and structures related to email headers and configurations

Newline characters and related errors

newline, carriage return, endl

No Comments

No Known Activations