INDEX

Explanations

structured data elements and their manipulation in coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Sha

-0.50

 Schoen

-0.49

Chi

-0.47

عاون

-0.46

Sch

-0.45

tingen

-0.45

maten

-0.45

CH

-0.45

ávat

-0.44

koła

-0.44

POSITIVE LOGITS

AndEndTag

1.10

GEBURTSDATUM

1.03

 Roskov

0.85

InjectAttribute

0.84

 ویکی‌پدیای

0.78

سطس

0.77

دانشنامهٔ

0.76

 CreateTagHelper

0.71

 itſelf

0.71

 AssemblyProduct

0.70

Activations Density 3.122%

structured data elements and their manipulation in coding

No Comments

No Known Activations