INDEX

Explanations

concepts related to personal growth, self-improvement, and accountability

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

Followed by "please" or similar politeness markers

np_acts-logits-general · gemini-2.0-flash

requests for information or action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 they

-0.44

≦)

-0.43

 recevrez

-0.41

してくれます

-0.39

__(/*!

-0.38

ようになります

-0.37

she

-0.36



-0.35

')[

-0.35

 она

-0.35

POSITIVE LOGITS

 please

1.20

please

0.97

 Please

0.95

 hãy

0.91

Please

0.90

 PLEASE

0.81

pls

0.79

plz

0.79

请

0.69

請

0.67

Activations Density 0.549%

concepts related to personal growth, self-improvement, and accountability

Followed by "please" or similar politeness markers

requests for information or action

No Known Activations

concepts related to personal growth, self-improvement, and accountability

Followed by "please" or similar politeness markers

requests for information or action

No Known Activations