INDEX

Explanations

the presence of the term "Me" in various contexts

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

Token "Me" followed by a capitalized token

np_acts-logits-general · gemini-2.0-flash

Me & various following tokens

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

expandindo

-0.53

vitis

-0.52

webElementXpaths

-0.49

NewGuid

-0.48

IntoConstraints

-0.47

ύν

-0.47

prefixer

-0.46

enumi

-0.45

stm

-0.45

 '\\;'

-0.45

POSITIVE LOGITS

 Meier

0.64

Me

0.64

Me

0.63

mybatisplus

0.61

CFS

0.57

 OFDb

0.57

UnsafeEnabled

0.54

Mé

0.53

 Megal

0.53

Mep

0.53

Activations Density 0.093%

the presence of the term "Me" in various contexts

Token "Me" followed by a capitalized token

Me & various following tokens

No Comments

No Known Activations