INDEX

Explanations

terms related to powers or abilities enhanced by technology and magic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

#+#

-1.00

évaluateur

-0.95

 <=",

-0.95

 utafitiHapana

-0.93

 EconPapers

-0.93

 CreateTagHelper

-0.93

 indisponible

-0.91

 الحره

-0.91

+:+

-0.90

 שוליים

-0.89

POSITIVE LOGITS

 Power

0.42

 Green

0.39

נס

0.38

 Grand

0.38

<!--

0.37

hintText

0.37

 matière

0.37

bjerg

0.37

 tome

0.36

 Zusammen

0.36

Activations Density 0.248%

terms related to powers or abilities enhanced by technology and magic

No Comments

No Known Activations