INDEX

Explanations

references to attributes in various contexts, particularly in programming and data structures

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

XML/programming attributes

np_acts-logits-general · gemini-2.0-flash

attribute definitions and access

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 voeten

-0.74

SourceChecksum

-0.69

/******/

-0.68

runApp

-0.65

 BorderRadius

-0.65

SuppressMessage

-0.64

endpush

-0.62

isOk

-0.61

rän

-0.60

 splen

-0.59

POSITIVE LOGITS

 attributes

1.24

 attribute

1.14

attributes

1.13

attribute

1.09

 Attributes

1.01

 Attribute

1.00

 properties

0.97

Attribute

0.97

 characteristics

0.90

AttributeSet

0.90

Activations Density 0.297%

references to attributes in various contexts, particularly in programming and data structures

XML/programming attributes

attribute definitions and access

No Comments

No Known Activations