INDEX

Explanations

phrases related to processes, measurements, and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

OfBirth

-0.48

 abandono

-0.48

 classé

-0.47

 parlent

-0.47

ValueStyle

-0.47

 stesse

-0.46

 peindre

-0.45

 mépris

-0.45

 históricas

-0.45

wijl

-0.45

POSITIVE LOGITS

 فريبيس

1.03

RegistryLite

0.91

Geplaatst

0.83

 GenerationType

0.81

ImageContext

0.79

EDEFAULT

0.77

 betweenstory

0.74

makeText

0.74

writerow

0.73

 препратки

0.70

Activations Density 1.110%

phrases related to processes, measurements, and evaluations

No Comments

No Known Activations