INDEX

Explanations

phrases related to division and classification within data or objects

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

ất

-0.54

 Coulomb

-0.51

iseaux

-0.50

oplan

-0.48

celli

-0.47

omal

-0.46

ubio

-0.46

 polymorphism

-0.46

galan

-0.46

useum

-0.46

POSITIVE LOGITS

tagHelperRunner

1.03

 protoimpl

0.78

 صوتيه

0.78

 separate

0.78

SequentialGroup

0.76

 seperate

0.76

 betweenstory

0.74

+#+#

0.73

 categories

0.72

Personensuche

0.71

Activations Density 0.356%

phrases related to division and classification within data or objects

No Comments

No Known Activations