INDEX

Explanations

code comments and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 happened

-0.60

 weren

-0.59

 occurred

-0.58

#!/

-0.53

 tourner

-0.49

 tombé

-0.48

 wasn

-0.48

 potranno

-0.47

instancetype

-0.47

 AudioClip

-0.46

POSITIVE LOGITS

 decide

0.58

 concede

0.56

rige

0.55

tanleria

0.54

SharedCtor

0.54

 produce

0.52

usa

0.51

 introduce

0.50

 divide

0.50

 define

0.50

Activations Density 0.034%

code comments and documentation

No Comments

No Known Activations