INDEX

Explanations

terms related to legal and regulatory frameworks

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

essential, intellectual, integrated, quality, wild, transition, operational, neural

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

帖最后由

-0.76

enumi

-0.65

 AssemblyCompany

-0.59

ronpa

-0.57

AlterField

-0.52

⟬

-0.52

 Deshalb

-0.52

ölkerung

-0.51

 HasFactory

-0.50

antMatchers

-0.50

POSITIVE LOGITS

CDCl

0.48

liſh

0.46

casio

0.45

uintptr

0.44

TiO

0.42

RenderAtEndOf

0.42

iſh

0.42

reinterpret

0.41

oplasmic

0.40

 Pseudo

0.39

Activations Density 1.600%

terms related to legal and regulatory frameworks

essential, intellectual, integrated, quality, wild, transition, operational, neural

No Comments

No Known Activations