INDEX

Explanations

terms related to loading states and statuses in a system or process

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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



-0.56

Tikang

-0.55

 дописавши

-0.55

jspb

-0.54

tagHelperRunner

-0.52

 BoxDecoration

-0.48

">//

-0.48

 tartalomajánló

-0.47

findpost

-0.47

domada

-0.47

POSITIVE LOGITS

 setLoading

0.37

isLoading

0.33

katapos

0.32

RenderAtEndOf

0.32

exhaus

0.32

 ſever

0.32

Чтоб

0.32

 volatility

0.32

isFetching

0.31

 ErrIntOverflow

0.31

Activations Density 0.002%

terms related to loading states and statuses in a system or process

No Comments

No Known Activations