INDEX

Explanations

programming-related keywords and structures associated with UI design and functionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

coltura

-0.51

 مخطط

-0.48

бур

-0.47

муля

-0.46

 multiple

-0.44

ễm

-0.43

Ligações

-0.43

 nothing

-0.43

Демо

-0.43

angliski

-0.43

POSITIVE LOGITS

DockStyle

0.95

 personalities

0.88

 Monfieur

0.84

 perfons

0.83

Efq

0.81

AndEndTag

0.77

 flies

0.75

 laſt

0.74

 preſent

0.74

 whoſe

0.74

Activations Density 2.847%

programming-related keywords and structures associated with UI design and functionality

No Comments

No Known Activations