INDEX

Explanations

phrases related to moral or ethical issues

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

natural qualifications and equal

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

webElementXpaths

-0.53

 typelib

-0.52

 continúas

-0.52

Хьажоргаш

-0.43

adaptiveStyles

-0.43

SharedCtor

-0.42

+#+#

-0.40

 houſe

-0.37

onAttach

-0.36

 utafitiHapana

-0.36

POSITIVE LOGITS

 informée

0.66

кобрита

0.57

Personensuche

0.56

IUrlHelper

0.55

点此举报

0.47

ьаж

0.47

Rhestr

0.46

 doInBackground

0.44

runApp

0.43

Aholisi

0.43

Activations Density 0.090%

phrases related to moral or ethical issues

natural qualifications and equal

No Comments

No Known Activations