INDEX

Explanations

operations and transformations related to data processing in Spark

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

<eos>

-0.42

 completed

-0.42

 reconstructed

-0.41

usel

-0.40

.[

-0.39

®

-0.39

とお

-0.39

良

-0.37

のお

-0.37

POSITIVE LOGITS

 JpaRepository

1.01

LookAnd

0.98

adpleegd

0.98

 CreateTagHelper

0.91

 mergeFrom

0.90

AndroidJUnit

0.89

aarrggbb

0.88

 Италијани

0.87

 للاسماء

0.87

ELTS

0.83

Activations Density 0.743%

operations and transformations related to data processing in Spark

No Comments

No Known Activations