INDEX

Explanations

command line options and help messages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

脚注の使い方

-0.61

NamedQueries

-0.50

ReusableCell

-0.49

 AspNetCore

-0.48

eared

-0.47

degree

-0.47

ikir

-0.46

rrggbb

-0.46

äsident

-0.46

Vinci

-0.46

POSITIVE LOGITS

Personendaten

0.82

 getopt

0.78

ConstraintMaker

0.78

DockStyle

0.73

 argparse

0.71

ArgumentParser

0.66

__":

0.65

](#

0.63

XmlSchema

0.61

UnusedPrivate

0.61

Activations Density 0.435%

command line options and help messages

No Comments

No Known Activations