INDEX

Explanations

references to mathematical theorems and lemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

googleapis

-0.49

Rohy

-0.48

 demas

-0.46

 Grá

-0.45

multer

-0.44

 PartialEq

-0.44

 ArrayAdapter

-0.43

grunt

-0.43

 tearDown

-0.43

sinon

-0.42

POSITIVE LOGITS

 AssemblyProduct

0.86

poons

0.69

 betweenstory

0.67

 estekak

0.60

 Paglinawan

0.60

 Normdatei

0.58

 kasarigan

0.58

مصادر

0.57

 Infórmanos

0.57

Diweddarwch

0.56

Activations Density 0.595%

references to mathematical theorems and lemmas

No Comments

No Known Activations