INDEX

Explanations

references to software updates and notifications

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

 also

-0.59

and

-0.59

 however

-0.52

 heller

-0.52

or

-0.50

 также

-0.50

 again

-0.46

いえ

-0.45

etc

-0.45

also

-0.45

POSITIVE LOGITS

 متعلقه

0.89

GEBURTSDATUM

0.88

rungsseite

0.87

 الحره

0.83

>--}}

0.81

 وتسجيلات

0.74

 مرئيه

0.73

RenderAtEndOf

0.73

niająca

0.72

 سكانية

0.72

Activations Density 0.038%

references to software updates and notifications

No Comments

No Known Activations