INDEX

Explanations

terms related to increases or improvements in measurements or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 negeri

-0.51

ha

-0.48

 manhã

-0.46

 blij

-0.43

 longues

-0.43

no

-0.43

 Prinzip

-0.43

 lunak

-0.42

 paciencia

-0.42

POSITIVE LOGITS

SourceChecksum

1.00

 Италијани

0.91

 BorderRadius

0.89

AddTagHelper

0.86

HasAnnotation

0.85

✨:

0.82

 كومونز

0.81

jfree

0.81

 NavController

0.81

$_.

0.80

Activations Density 0.881%

terms related to increases or improvements in measurements or conditions

No Comments

No Known Activations