INDEX

Explanations

mathematical symbols and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

aarrggbb

-0.67

-0.60

 onCreateView

-0.60

IDE

-0.59

-0.58

hev

-0.58

-0.57

ctools

-0.57

flatMap

-0.56

 Kund

-0.55

POSITIVE LOGITS

$(

1.29

($(

1.16

 againſt

1.14

 whoſe

1.01

 coö

1.01

 itſelf

0.99

}}(

0.98

$_(

0.98

 faſt

0.97

 Theſe

0.97

Activations Density 0.402%

mathematical symbols and notation

No Comments

No Known Activations