INDEX

Explanations

specific scientific and technical terms or acronyms related to research and classifications

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

webElementXpaths

-0.33

flush

-0.29

styleable

-0.29

esModule

-0.28

↵↵

-0.26

<strong>

-0.25

om

-0.25

↵

-0.25

 Corn

-0.25

-0.24

POSITIVE LOGITS

 müſſen

0.76

ſelf

0.75

 laſſen

0.75

ſelves

0.74

 ſelbſt

0.73

 ſeine

0.73

 verſch

0.70

 geſch

0.68

 Infórmanos

0.68

Ikus

0.68

Activations Density 0.078%

specific scientific and technical terms or acronyms related to research and classifications

No Comments

No Known Activations