INDEX

Explanations

terms related to cost-effectiveness and pricing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

createServer

-0.45

setColumns

-0.45

 TextInputType

-0.43

 endor

-0.42

 GetEnumerator

-0.41

irus

-0.40

ValueStyle

-0.40

AfterViewInit

-0.40

лл

-0.39

toByteArray

-0.38

POSITIVE LOGITS

 cheap

2.92

 cheaper

2.73

 inexpensive

2.61

cheap

2.52

 cheapest

2.49

Cheap

2.40

 Cheap

2.39

 cheaply

2.36

 affordable

2.32

 Cheaper

2.23

Activations Density 0.382%

terms related to cost-effectiveness and pricing

No Comments

No Known Activations