INDEX

Explanations

keywords related to reader engagement and feedback

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

Followed by prepositions, conjunctions, or punctuation

np_acts-logits-general · gemini-2.0-flash

letters and readers

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

 dettaglio

-0.54

SharedCtor

-0.53

Personensuche

-0.51

 Negotiation

-0.49

 retrouve

-0.49

.*")]

-0.48

 cardíaca

-0.47

romyal

-0.47

 mestre

-0.46

 stappen

-0.46

POSITIVE LOGITS

 reader

1.03

 listener

1.00

 readers

0.99

 Readers

0.91

Readers

0.86

 Reader

0.84

 listeners

0.82

 submitted

0.81

 submissions

0.79

 Listener

0.78

Activations Density 0.233%

keywords related to reader engagement and feedback

Followed by prepositions, conjunctions, or punctuation

letters and readers

No Comments

No Known Activations