INDEX

Explanations

temporal references indicating events relative to each other

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ARGV

-0.57

UNE

-0.55

 multip

-0.52

 number

-0.50

gany

-0.49

inty

-0.49

ribut

-0.48

Sen

-0.48

 Wanda

-0.48

Fen

-0.47

POSITIVE LOGITS

AndEndTag

0.90

GEBURTSDATUM

0.88

 betweenstory

0.85

ViewImports

0.79

 ExecuteAsync

0.73

出版年

0.73

AnimationsModule

0.72

 Paglinawan

0.72

SharedCtor

0.72

fromnode

0.71

Activations Density 0.134%

temporal references indicating events relative to each other

No Comments

No Known Activations