INDEX

Explanations

terms and commands related to canceling or quitting actions

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

"Quit," "cancel," or "exit" actions

np_acts-logits-general · gemini-2.0-flash

quitting, cancelling, or dismissing

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

AssignableFrom

-0.54

APORE

-0.53

hydrates

-0.51

 poveznice

-0.50

orteur

-0.49

GPI

-0.48

 Réponses

-0.48

 finisher

-0.47

ernalia

-0.47

LTD

-0.46

POSITIVE LOGITS

掉

0.78

 gracefully

0.72

Reason

0.67

 premat

0.67

掉的

0.66

Reasons

0.65

MemoryWarning

0.61

 reaſon

0.60

MethodManager

0.59

 reason

0.57

Activations Density 0.214%

terms and commands related to canceling or quitting actions

"Quit," "cancel," or "exit" actions

quitting, cancelling, or dismissing

No Comments

No Known Activations