INDEX

Explanations

occurrences of images or graphic elements represented by HTML tags and their associated attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 utafitiHapana

-0.96

ItemBackground

-0.95

 Winaray

-0.91

 unknownFields

-0.90

CppCodeGen

-0.88

 Wiktionnaire

-0.87

SharedDtor

-0.86

 Administrativna

-0.85

цездатний

-0.83

CWE

-0.82

POSITIVE LOGITS

 الاطلاع

0.59

czeniu

0.48

 voks

0.45

 følge

0.42

 chimiques

0.42

 jovens

0.41

 encontram

0.40

 рода

0.39

つづく

0.39

 jóvenes

0.37

Activations Density 0.007%

occurrences of images or graphic elements represented by HTML tags and their associated attributes

No Comments

No Known Activations