INDEX

Explanations

references to stars and their significance in various 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

 OnInit

-0.47

 위한

-0.44

⇓

-0.39

########.

-0.39

 دى

-0.38

licted

-0.37

Preamble

-0.37

ngOnInit

-0.37

🟩

-0.36

 entailed

-0.36

POSITIVE LOGITS

 Stars

0.89

 star

0.88

 stars

0.87

Stars

0.86

 STAR

0.83

Star

0.81

 étoiles

0.79

 Starlight

0.79

 Star

0.77

stars

0.77

Activations Density 0.403%

references to stars and their significance in various contexts

No Comments

No Known Activations