INDEX

Explanations

elements related to structured data or programming constructs

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

исленность

-0.71

hassee

-0.56

arnes

-0.56

Addo

-0.54

milan

-0.53

 Tind

-0.52

ItemBackground

-0.52

 disambiguazione

-0.51

 ninth

-0.49

ΑΣ

-0.49

POSITIVE LOGITS

makeText

0.68

 BoxFit

0.64

geist

0.64

CodeAttribute

0.63

 CURIAM

0.55

MemoryWarning

0.53

ISCHE

0.47

viewDidLoad

0.47

fjspx

0.47

 Lordships

0.47

Activations Density 0.137%

elements related to structured data or programming constructs

No Comments

No Known Activations