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 @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

tagHelperRunner

-0.56

nefs

-0.52

-0.51

sequential

-0.50

--

-0.49

 intptr

-0.49

*/}

-0.48

';

-0.47

"]/

-0.47

umann

-0.47

POSITIVE LOGITS

XmlEnum

0.74

adaptiveStyles

0.73

SpringRunner

0.67

 متعلقه

0.65

cell

0.61

TypedDataSet

0.60

ReusableCell

0.60

hoeddwyd

0.59

✭✭

0.58

 gyhoeddwyd

0.57

Activations Density 2.395%

mathematical symbols and notation

No Comments

No Known Activations