INDEX

Explanations

technical terms and issues related to software, medical conditions, and manufacturing processes

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

-0.41

 eccell

-0.41

 quæ

-0.40

-0.39

-0.38

 hilsen

-0.38

 toscana

-0.37

 totalidad

-0.37

řízen

-0.36

Rä

-0.36

POSITIVE LOGITS

Personendaten

0.98

 متعلقه

0.90

UnusedPrivate

0.88

AndEndTag

0.86

clusal

0.84

PreferredItem

0.83

Datuak

0.83

 EconPapers

0.81

yntaxException

0.80

culoskeletal

0.80

Activations Density 0.721%

technical terms and issues related to software, medical conditions, and manufacturing processes

No Comments

No Known Activations