INDEX

Explanations

code related to Android app components and lifecycle methods

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

do

-0.56

be

-0.46

-0.44

Sp

-0.44

tfrac

-0.43

 pack

-0.43

and

-0.43

</i>

-0.43

ables

-0.43

pri

-0.43

POSITIVE LOGITS

ValueStyle

1.84

RenderAtEndOf

1.80

 viewDidLoad

1.66

GraphicsUnit

1.66

setContentView

1.50

AddHtmlAttribute

1.47

CloseOperation

1.43

templateUrl

1.43

BeginContext

1.43

ngOnInit

1.33

Activations Density 0.005%

code related to Android app components and lifecycle methods

No Comments

No Known Activations