INDEX

Explanations

references to classes and objects in programming code

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

Objective-C or Swift code imports

np_acts-logits-general · gemini-2.0-flash

Objective-C imports and declarations

np_acts-logits-general · gemini-2.5-flash-lite

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

ⓧ

-0.68

BeginContext

-0.61

principalTable

-0.51

enumii

-0.49

tagHelperRunner

-0.49

RegressionTest

-0.47

 للاسماء

-0.46

ReferenceEquals

-0.43

DebuggerNonUser

-0.42

 Delia

-0.41

POSITIVE LOGITS

 tartalomajánló

0.75

 Савезне

0.71

 himo

0.67

 Italijani

0.64

0.60

endpush

0.59

 endblock

0.59

ksesta

0.56

ENDENT

0.55

IBS

0.55

Activations Density 0.124%

references to classes and objects in programming code

Objective-C or Swift code imports

Objective-C imports and declarations

No Comments

No Known Activations