INDEX

Explanations

references to significant historical dates or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

//

-0.93

IsMutable

-0.83

UserScript

-0.78

<?

-0.74

FormTagHelper

-0.72

-0.69

richTextPanel

-0.68

 myſelf

-0.68

 protoimpl

-0.67

}],

-0.67

POSITIVE LOGITS

0.72

’

0.61

0.60

ies

0.57

年代

0.54

es

0.53

ết

0.50

′

0.46

´

0.46

0.43

Activations Density 0.077%

references to significant historical dates or events

No Comments

No Known Activations