INDEX

Explanations

programming-related terminology and syntax

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

Command-line argument parsing

np_acts-logits-general · gemini-2.0-flash

command line arguments and parsing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.47

RTLR

-0.44

RTHOOK

-0.43

awtextra

-0.41

scribers

-0.39

dbo

-0.39

dflare

-0.39

OGND

-0.39

 plafond

-0.38

ReusableCell

-0.38

POSITIVE LOGITS

ArgumentParser

1.09

 argparse

0.73

SBATCH

0.68

yargs

0.66

routeProvider

0.63

ItemBackground

0.56

stateProvider

0.55

HomeAsUpEnabled

0.53

optarg

0.46

cobra

0.46

Activations Density 0.198%

programming-related terminology and syntax

Command-line argument parsing

command line arguments and parsing

No Comments

No Known Activations