INDEX

Explanations

terms and phrases related to model building and mathematical modeling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

sizeCache

-0.70

 modeled

-0.61

 modelled

-0.60

+#+#

-0.57

oa̍t

-0.56

ParallelGroup

-0.55

 незавершена

-0.55

 >=",

-0.55

protoimpl

-0.55

IBarButtonItem

-0.54

POSITIVE LOGITS

er

0.78

led

0.77

lierung

0.63

 ModelExpression

0.62

erna

0.57

ER

0.57

 organism

0.56

링

0.56

isation

0.56

 railroad

0.54

Activations Density 0.141%

terms and phrases related to model building and mathematical modeling

No Comments

No Known Activations