INDEX

Explanations

the presence of specific markers or tokens indicating the beginning of a new section or context in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kasarigan

-0.68

AndEndTag

-0.67

 noqa

-0.59

Aiheesta

-0.51

bosity

-0.48

__':

-0.47

taine

-0.46

 بيها

-0.46

 colle

-0.46

सा

-0.46

POSITIVE LOGITS

 autorytatywna

0.76

AndroidJUnit

0.66

 fermés

0.66

✨:

0.60

setVerticalGroup

0.60

 habet

0.58

 ejus

0.57

 infecciones

0.57

 potest

0.55

Autoritní

0.55

Activations Density 0.088%

the presence of specific markers or tokens indicating the beginning of a new section or context in the text

No Comments

No Known Activations