INDEX

Explanations

elements related to logical or conditional operators in programming code

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

EndInit

-0.58

’”

-0.56

]"

-0.56

!]

-0.56

NSIndexPath

-0.55

NSString

-0.54

'"

-0.53

reactivex

-0.52

ünkü

-0.52

 also

-0.52

POSITIVE LOGITS

sizeCache

0.86

tagHelperRunner

0.84

Hozzáférés

0.76

 &___

0.74

CloseOperation

0.73

InjectAttribute

0.73

*)&

0.72

 CreateTagHelper

0.71

sī

0.69

enumii

0.67

Activations Density 0.051%

elements related to logical or conditional operators in programming code

No Comments

No Known Activations