INDEX

Explanations

programming constructs related to data structures and methods

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

出版年

-0.81

 للاسماء

-0.77

 незавершена

-0.69

sizeCache

-0.64

 CreateTagHelper

-0.63

WriteTagHelper

-0.63

bootstrapcdn

-0.61

'{@

-0.54

İstinadlar

-0.52

internalType

-0.52

POSITIVE LOGITS

 Integer

1.46

Integer

1.44

 Boolean

1.00

Boolean

0.92

 String

0.86

String

0.85

NSNumber

0.82

Float

0.81

 Long

0.81

Long

0.80

Activations Density 0.056%

programming constructs related to data structures and methods

No Comments

No Known Activations