INDEX

Explanations

variables and their associated notation in mathematical equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

plain

-0.70

tagext

-0.68

hex

-0.65

Hex

-0.64

Hex

-0.62

UIControlState

-0.60

hex

-0.59

 plain

-0.58

 насеље

-0.56

setVerticalGroup

-0.55

POSITIVE LOGITS

出版年

0.60

enschaften

0.58

}_{+

0.56

habits

0.55

]?.

0.54

 occupied

0.54

Hochspringen

0.54

INERY

0.53

 pageContext

0.51

antaine

0.51

Activations Density 1.130%

variables and their associated notation in mathematical equations

No Comments

No Known Activations