INDEX

Explanations

phrases indicating additional information or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 stata

-0.47

 bề

-0.46

millimeters

-0.46

Roberts

-0.45

cina

-0.44

RRect

-0.44

 equation

-0.44

 Umgang

-0.43

 Draw

-0.43

ppa

-0.42

POSITIVE LOGITS

__':

0.73

 Мексичка

0.71

 >=",

0.70

 ویکی‌پدیای

0.69

__":

0.69

ioutil

0.68

StructEnd

0.67

 Normdatei

0.67

 مرئيه

0.65

 المعيارى

0.64

Activations Density 0.602%

phrases indicating additional information or examples

No Comments

No Known Activations