INDEX

Explanations

programming-related terms, particularly those associated with templates, internal structures, and detailed implementation aspects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stateProvider

-0.97

CreateMap

-0.85

MessageOf

-0.79

httphttps

-0.79

elemField

-0.79

URLException

-0.75

ISupport

-0.74

 Италијани

-0.73

IndentedString

-0.72

FieldDescriptor

-0.70

POSITIVE LOGITS

internal

0.76

Internal

0.72

 internal

0.67

INTERNAL

0.65

 Internal

0.64

Попис

0.58

 underlying

0.57

Impl

0.56

DaoImpl

0.53

igshid

0.52

Activations Density 0.265%

programming-related terms, particularly those associated with templates, internal structures, and detailed implementation aspects

No Comments

No Known Activations