INDEX

Explanations

numerical values across various contexts

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

GP

-0.59

ו

-0.56

чі

-0.53

 Bigger

-0.53

 ElementRef

-0.53

mybatisplus

-0.52

orks

-0.52

 Abbé

-0.52

 György

-0.51

 herre

-0.51

POSITIVE LOGITS

setViewportView

0.78

-------

0.78

abestanden

0.72

endphp

0.71

<bos>

0.70

!*\

0.70

);

0.70

UnknownFieldSet

0.69

.)}

0.68

/***/

0.67

Activations Density 0.414%

numerical values across various contexts

No Comments

No Known Activations