INDEX

Explanations

terms related to XML attributes and their handling

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

arraycopy

-0.77

 grátis

-0.72

 Reus

-0.68

RTLU

-0.68

 Offisielt

-0.67

Looper

-0.66

 pesce

-0.65

SourceChecksum

-0.64

 tôt

-0.64

 Holman

-0.64

POSITIVE LOGITS

 attribute

2.99

attribute

2.74

 attributes

2.63

 Attribute

2.56

attributes

2.45

Attribute

2.37

 Attributes

2.33

Attributes

2.16

 attribut

1.97

ATTRIBUTE

1.85

Activations Density 0.052%

terms related to XML attributes and their handling

No Comments

No Known Activations