INDEX

Explanations

code segments related to operations on data structures and user interface elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 IconData

-0.60

awtextra

-0.60

FormUrlEncoded

-0.60

requestCode

-0.58

 betweenstory

-0.58

 kasarigan

-0.57

ثيق

-0.56

 Pelt

-0.55

DataPropertyName

-0.55

 تانيه

-0.55

POSITIVE LOGITS

 chi̍t

0.55

例句

0.55

 Wicidata

0.53

abestanden

0.53

 الرخصة

0.50

RTLR

0.47

ReferenceEquals

0.47

WithMany

0.46

Hentet

0.45

XmlAccessorType

0.45

Activations Density 0.117%

code segments related to operations on data structures and user interface elements

No Comments

No Known Activations