INDEX

Explanations

programming-related constructs and elements, particularly focusing on data structures and UI elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tagHelperRunner

-0.79

OGND

-0.78

 AssemblyTitle

-0.66

interopRequire

-0.63

 defaultstate

-0.63

 ſtate

-0.60

 referrerpolicy

-0.60

ValueStyle

-0.59

出版年

-0.59

GOTREF

-0.57

POSITIVE LOGITS

preloader

0.37

 Myron

0.36

 flare

0.36

 CURLOPT

0.35

def

0.35

 reactions

0.35

 Whelan

0.35

 Gerv

0.35

vertret

0.35

lob

0.34

Activations Density 0.814%

programming-related constructs and elements, particularly focusing on data structures and UI elements

No Comments

No Known Activations