INDEX

Explanations

references to items and their function in storage or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

❯

-0.44

reactstrap

-0.43

TypedDataSet

-0.41

PRNewswire

-0.38

навли

-0.37

 Italijanski

-0.37

 Freitas

-0.37

 ObjectParameter

-0.37

 imóvel

-0.36

POSITIVE LOGITS

bag

0.63

 luggage

0.60

 bags

0.60

 MainAxisSize

0.59

 handbag

0.56

 wallet

0.55

WriteTagHelper

0.55

 wallets

0.54

 pouches

0.54

 accessories

0.52

Activations Density 0.134%

references to items and their function in storage or organization

No Comments

No Known Activations