INDEX

Explanations

references and citations related to edited volumes and anthologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

出版年

-0.70

ConstraintMaker

-0.62

ngdoc

-0.60

insurance

-0.59

 Signalez

-0.58

 nebula

-0.57

RegressionTest

-0.57

:]:

-0.56

toObject

-0.55

PhysRevLett

-0.55

POSITIVE LOGITS

 disambiguazione

0.57

 Introduce

0.51

 CONTRIBUTORS

0.50

 Introducing

0.47

 introducing

0.47

 tématu

0.44

 introduces

0.43

 contributors

0.43

IsContent

0.42

 featuring

0.42

Activations Density 0.232%

references and citations related to edited volumes and anthologies

No Comments

No Known Activations