INDEX

Explanations

references to medical conditions and their implications

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ReusableCell

-0.56

defineProperty

-0.54

Життєпис

-0.49

értelmű

-0.48

 AssemblyTitle

-0.47

 abraço

-0.46

RefreshLayout

-0.45

 publicados

-0.45

 Partager

-0.43

 possano

-0.43

POSITIVE LOGITS

IndentedString

0.69

 nakalista

0.66

 estekak

0.65

 saites

0.65

nodoc

0.64

 EClass

0.62

:✨

0.59

)++;

0.58

 Catawiki

0.58

 nonatomic

0.57

Activations Density 0.535%

references to medical conditions and their implications

No Known Activations