INDEX

Explanations

codes and identifiers in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

تقاوى

-0.75

ंदीखरीदारी

-0.55

matchCondition

-0.49

 الاطلاع

-0.49

 يتيمه

-0.48

 resourceCulture

-0.48

 autorytatywna

-0.48

rungsseite

-0.47

 PagesJaunes

-0.47

 cherchés

-0.47

POSITIVE LOGITS

PointerException

0.45

StateException

0.44

 Warfare

0.43

 Paglinawan

0.42

chowa

0.39

 behalten

0.39

IBarButtonItem

0.38

 Spie

0.38

mascar

0.38

addLast

0.38

Activations Density 0.041%

codes and identifiers in programming contexts

No Comments

No Known Activations