INDEX

Explanations

verbs and phrases indicating modifications or changes, particularly in technical or descriptive contexts

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

-0.92

enumi

-0.89

enumii

-0.84

 transfieras

-0.78

Datuak

-0.78

 transférez

-0.77

AndroidJUnit

-0.74

anskje

-0.71

 Reſ

-0.71

ьаж

-0.71

POSITIVE LOGITS

IntoConstraints

0.53

 area

0.47

IBarButtonItem

0.45

 section

0.42

reactstrap

0.41

部分

0.39

ClientRect

0.39

 bawah

0.36

bereich

0.36

әне

0.36

Activations Density 0.725%

verbs and phrases indicating modifications or changes, particularly in technical or descriptive contexts

No Comments

No Known Activations