INDEX

Explanations

phrases indicating a state of being or condition, especially those denoting emotional or situational contexts

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

"in" followed by a noun

np_acts-logits-general · gemini-2.0-flash

in a condition

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

Vidite

-0.77

seamnă

-0.67

 Italijanski

-0.67

windowFixed

-0.66

 للمعارف

-0.62

 مشارکت‌کنندگان

-0.61

 ddelweddau

-0.61

 nakalista

-0.59

README

-0.59

 HomeComponent

-0.57

POSITIVE LOGITS

 charge

1.15

 need

0.95

 possession

0.85

 touch

0.82

 danger

0.81

 contact

0.81

 trouble

0.80

charge

0.79

 control

0.77

 receipt

0.74

Activations Density 0.240%

phrases indicating a state of being or condition, especially those denoting emotional or situational contexts

"in" followed by a noun

in a condition

No Comments

No Known Activations