INDEX

Explanations

phrases indicating adherence to guidelines or standards

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

follow Every, <start_of_turn> user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 fieldNum

-0.39

 idéia

-0.35

SourceChecksum

-0.35

cein

-0.34

 contained

-0.34

 autorytatywna

-0.34

 Sementara

-0.34

 sementara

-0.33

 Shimizu

-0.33

 older

-0.33

POSITIVE LOGITS

:✨

0.71

 queſta

0.56

ंदीखरीदारी

0.56

 الرياضيه

0.53

VYMaps

0.52

StructEnd

0.49

 ویکی‌پدی

0.49

хьтан

0.48

 protoimpl

0.47



0.46

Activations Density 0.000%

phrases indicating adherence to guidelines or standards

follow Every, <start_of_turn> user

No Comments

No Known Activations