INDEX

Explanations

references to historical inventions and their inventors

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

évaluateur

-0.74

-0.65

WebElementEntity

-0.63

transporter

-0.61

ppuden

-0.61

 postmodern

-0.60

 AssemblyProduct

-0.60

 polyurethane

-0.59

 stoichio

-0.58

siębior

-0.58

POSITIVE LOGITS

WWI

0.71

 cloche

0.49

 Woodrow

0.48

gatsby

0.48

 referenties

0.47

 propOrder

0.46

WebServlet

0.45

serviceWorker

0.45

waitKey

0.42

 suffrage

0.42

Activations Density 0.564%

references to historical inventions and their inventors

No Comments

No Known Activations