INDEX

Explanations

terms related to licensing and legal documentation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

epam

-0.48

 livraison

-0.47

%";

-0.47

 nač

-0.46

burger

-0.46

toise

-0.45

 فريبيس

-0.45

UKU

-0.44

uating

-0.44

tiglia

-0.43

POSITIVE LOGITS

Cyfeiriadau

0.78

 typelib

0.76

InjectAttribute

0.76

 transfieras

0.73

 belonged

0.73

RegressionTest

0.72

DataAnnotations

0.71

 belongs

0.70

 belong

0.65

]")]

0.65

Activations Density 0.002%

terms related to licensing and legal documentation

No Known Activations