INDEX

Explanations

references to mathematical notation and definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

̍

-0.55

NameInMap

-0.52

 CascadeType

-0.49

EFAULT

-0.49

FetchType

-0.48

 Geraadpleegd

-0.48

https

-0.47

strix

-0.47

GeneratedValue

-0.47

//-->

-0.47

POSITIVE LOGITS

 notation

0.83

rungsseite

0.76

notation

0.70

 Notation

0.67

 symbols

0.64

 symbol

0.64

 AssemblyCulture

0.64

 notations

0.61

símbolo

0.60

 Zacks

0.57

Activations Density 0.752%

references to mathematical notation and definitions

No Comments

No Known Activations