INDEX

Explanations

phrases indicating participation or involvement in various contexts or activities

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

"In" followed by nouns/activities

np_acts-logits-general · gemini-2.0-flash

participate in work or activity

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Monfieur

-0.67

 myſelf

-0.64

 poffe

-0.63

Efq

-0.61

ượu

-0.59

 itſelf

-0.58

 pleaſure

-0.57

 paff

-0.56

isable

-0.55

νώ

-0.55

POSITIVE LOGITS

WebElementEntity

0.65

WithIOException

0.61

ConstraintMaker

0.59

 незавершена

0.56

 scenes

0.56

 discussions

0.56

 Biôgrafia

0.56

ệc

0.56

RTEE

0.53

scenes

0.52

Activations Density 0.280%

phrases indicating participation or involvement in various contexts or activities

"In" followed by nouns/activities

participate in work or activity

No Comments

No Known Activations