INDEX

Explanations

phrases related to actions taken without the intention of publicity or recognition

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للمعارف

-0.63

 فريبيس

-0.62

存于互联网档案馆

-0.57

parsedMessage

-0.54

发表于

-0.53

ḵ

-0.51

 part

-0.51

__*/

-0.50

ureusement

-0.49

GeoNames

-0.49

POSITIVE LOGITS

 simply

2.13

simply

1.94

Simply

1.84

 merely

1.81

 Simply

1.81

 simplemente

1.79

 simplement

1.67

 semplicemente

1.64

 just

1.63

 просто

1.62

Activations Density 0.529%

phrases related to actions taken without the intention of publicity or recognition

No Comments

No Known Activations