INDEX

Explanations

prepositions and their associated phrases in the context of positions or roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Kuan

-0.49

 Arund

-0.47

 Tack

-0.46

 tack

-0.46

 Combien

-0.45

 toler

-0.44

 gauss

-0.44

abe

-0.43

 Polit

-0.43

taf

-0.42

POSITIVE LOGITS

 StatelessWidget

0.79

styleable

0.77

RenderAtEndOf

0.75

 NDEBUG

0.73

 AssemblyTitle

0.73

balleur

0.71

IUrlHelper

0.70

DataAnnotations

0.66

UnitTesting

0.66

municipi

0.65

Activations Density 0.174%

prepositions and their associated phrases in the context of positions or roles

No Comments

No Known Activations