INDEX

Explanations

technical and mathematical terminology related to structures, conditions, and robustness in machine learning and statistical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 itself

-0.73

__':

-0.73

itself

-0.68

SourceChecksum

-0.68

 kuris

-0.68

__':

-0.63

is

-0.62

its

-0.62

 которому

-0.62

Its

-0.61

POSITIVE LOGITS

 themselves

1.58

themselves

1.28

are

1.08

 cherchés

1.05

 were

0.91

 those

0.87

 jotka

0.87

 amelyek

0.83

 אלו

0.82

 אלה

0.81

Activations Density 2.761%

technical and mathematical terminology related to structures, conditions, and robustness in machine learning and statistical models

No Comments

No Known Activations