INDEX

Explanations

terms related to forward movement or progression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 vell

-0.46

 foli

-0.41

 Brilliant

-0.41

 useRouter

-0.40

 Gout

-0.40

 nere

-0.39

eas

-0.39

Cea

-0.38

 beaut

-0.37

 Litter

-0.37

POSITIVE LOGITS

Forward

0.85

 Forward

0.75

 FORWARD

0.71

wards

0.68

 forwards

0.66

 forward

0.66

forward

0.66

 propOrder

0.63

 outwards

0.63

########.

0.63

Activations Density 0.248%

terms related to forward movement or progression

No Comments

No Known Activations