INDEX

Explanations

occurrences of the word "Net" and various version notations related to software or programming 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

EndContext

-0.90

parsedMessage

-0.89

 مشين

-0.88

Autoritní

-0.79

ViewFeatures

-0.79

 Normdatei

-0.74

bootstrapcdn

-0.72

 SEDS

-0.72

fromCharCode

-0.70

elemField

-0.69

POSITIVE LOGITS

</thead>

0.60

lana

0.53

 Höchst

0.51

 Generales

0.50

ikes

0.49

 StatefulWidget

0.49

tal

0.49

vious

0.46

Eyes

0.46

Activations Density 0.029%

occurrences of the word "Net" and various version notations related to software or programming contexts

No Comments

No Known Activations