INDEX

Explanations

references to routers in a network context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

__':

-0.35

 intStringLen

-0.35

 Regno

-0.32

 parution

-0.32

 Carey

-0.30

bł

-0.29

évaluateur

-0.29

ッソ

-0.28

'])

-0.28

__':

-0.28

POSITIVE LOGITS

router

2.75

 Router

2.75

 router

2.69

Router

2.67

 routers

2.17

routers

1.82

 ROUT

1.79

 useRouter

1.66

 Routing

1.66

ROUT

1.63

Activations Density 0.028%

references to routers in a network context

No Comments

No Known Activations