INDEX

Explanations

references to winning or losing in various competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

存于互联网档案馆

-0.65

HasAnnotation

-0.58

AnchorStyles

-0.57

styleType

-0.56

 javafx

-0.54

']);

-0.54

ArgsConstructor

-0.53

 gyhoeddwyd

-0.53

 success

-0.53

successful

-0.52

POSITIVE LOGITS

 bataille

0.88

 battles

0.84

 battle

0.74

 batalla

0.70

 wars

0.70

 debates

0.64

 Battle

0.63

 batalha

0.62

 battaglia

0.61

 WARS

0.59

Activations Density 0.197%

references to winning or losing in various competitive contexts

No Comments

No Known Activations