INDEX

Explanations

numerical values or data points

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 GenerationType

-0.83

didSet

-0.81

awtextra

-0.80

mybatisplus

-0.78

CppMethod

-0.74

 propOrder

-0.67

 ainfi

-0.67

TintMode

-0.66

 <=",

-0.65

endphp

-0.65

POSITIVE LOGITS

 Paglinawan

0.57

座

0.54

carta

0.51

ОВА

0.50

CreateMap

0.50

вига

0.48

тере

0.46

teva

0.46

>()

0.45

 propri

0.45

Activations Density 0.141%

numerical values or data points

No Comments

No Known Activations