INDEX

Explanations

references to mathematical concepts, particularly in the context of filters and topology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.35.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

WithIOException

-0.47

pecabe

-0.47

WireFormatLite

-0.41

Governing

-0.38

 PyTuple

-0.38

 Taktlose

-0.38

IndentedString

-0.38

 stepmother

-0.36

grenze

-0.36

mutlich

-0.36

POSITIVE LOGITS

 تضيفلها

0.71

 topology

0.61

 topo

0.52

 TOPOLOGY

0.51

CloseOperation

0.51

topo

0.51

 Topology

0.51

topology

0.50

 Zorn

0.50

 metric

0.48

Activations Density 1.641%

references to mathematical concepts, particularly in the context of filters and topology

No Comments

No Known Activations