INDEX

Explanations

lines of code or syntax elements in programming contexts

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

 Roskov

-0.90

CloseOperation

-0.85

 CreateTagHelper

-0.81

TestingModule

-0.77

Попис

-0.74

 Soko

-0.74

……"

-0.73

NameInMap

-0.70

Gambas

-0.70

 مشين

-0.69

POSITIVE LOGITS

@@

2.48

@@

1.80

#+#

0.96

 sklearn

0.82

AlterField

0.78

urlpatterns

0.62

AutoScale

0.61

KeyPair

0.60

endsection

0.60

@@@

0.57

Activations Density 0.022%

lines of code or syntax elements in programming contexts

No Comments

No Known Activations