INDEX

Explanations

references to mathematical proofs and inequalities

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

SourceChecksum

-0.67

 Wikimedijinoj

-0.66

hoeddwyd

-0.65

Datuak

-0.59

 '\\;'

-0.56

WebVitals

-0.56

AsUp

-0.56

Rujuakan

-0.55

QMetaType

-0.54

Organisateur

-0.54

POSITIVE LOGITS

 scope

0.42

 trial

0.40

 secondary

0.38

 logically

0.37

 relax

0.36

 SECONDARY

0.35

 forward

0.35

 primary

0.34

 manageable

0.34

 آنجا

0.34

Activations Density 1.900%

references to mathematical proofs and inequalities

No Comments

No Known Activations