INDEX

Explanations

phrases related to permissions and licensing in software and data usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.76

-0.72

and

-0.68

be

-0.67

-0.61

the

-0.60

one

-0.59

to

-0.58

 much

-0.58

-0.57

POSITIVE LOGITS

IUrlHelper

1.31

Efq

1.25

 ་་

1.25

 CreateTagHelper

1.24

تقاوى

1.24

 Shakspeare

1.21

TypedDataSet

1.20

 متعلقه

1.19

 NSCoder

1.17

 ſind

1.16

Activations Density 0.231%

phrases related to permissions and licensing in software and data usage

No Comments

No Known Activations