INDEX

Explanations

coding constructs and programming-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

expandindo

-0.35

devamını

-0.35

 EconPapers

-0.34

 AssemblyCulture

-0.33

 defaultstate

-0.32

 hennes

-0.32

Хьажоргаш

-0.32

ūrė

-0.31

/**

-0.31

ArrowToggle

-0.31

POSITIVE LOGITS

 iconLine

0.62

SOUNDBITE

0.60

期刊论文

0.56



0.56

NameInMap

0.55

 intptr

0.54

клопе

0.51

Hopkins

0.50

optimal

0.50

 hObject

0.50

Activations Density 0.852%

coding constructs and programming-related terminology

No Comments

No Known Activations