INDEX

Explanations

references to specific structured data elements and attributes, often in programming or database contexts

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

 theils

-0.38

ukkig

-0.38

timately

-0.38

wahati

-0.38

érité

-0.37

 CURIAM

-0.36

cipar

-0.35

anyahu

-0.35

 município

-0.35

 régionale

-0.35

POSITIVE LOGITS

хьтан

0.79

 فريبيس

0.75

 NSCoder

0.65

 ویکی‌پدی

0.65

hoeddwyd

0.59

 CanadaChoose

0.56

 dAtA

0.56

 виправивши

0.54

دانشنامهٔ

0.54

Välislingid

0.52

Activations Density 0.963%

references to specific structured data elements and attributes, often in programming or database contexts

No Comments

No Known Activations