INDEX

Explanations

concepts related to logical problem solving and combinatorial optimization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

__(/*!

-0.45

addCriterion

-0.42

liceerd

-0.42

SPATH

-0.41

PreInfinity

-0.40

WriteBarrier

-0.40

ioutil

-0.38

XmlAccessType

-0.37

leicht

-0.37

orsese

-0.37

POSITIVE LOGITS

Sudoku

0.65

 Sudoku

0.56

 sudoku

0.52

sudoku

0.51

Diwedd

0.45

Zodiac

0.45

stdc

0.44

 susu

0.43

yntaxException

0.42

 Finishing

0.41

Activations Density 0.357%

concepts related to logical problem solving and combinatorial optimization

No Comments

No Known Activations