INDEX

Explanations

structured testing code, particularly with annotations and associated functions

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

 ModelExpression

-0.51

AsUp

-0.51

SharedDtor

-0.49

 fotográfica

-0.48

orcid

-0.47

 fejles

-0.47

 segreto

-0.46

 Heidegger

-0.46

createForm

-0.45

tagHelperRunner

-0.45

POSITIVE LOGITS

NewLabel

0.80

сылкі

0.68

 propOrder

0.66

TestMethod

0.65

Anm

0.64

shtml

0.63

maline

0.62

 مرئيه

0.62

BeginContext

0.61

httphttps

0.61

Activations Density 0.076%

structured testing code, particularly with annotations and associated functions

No Comments

No Known Activations