INDEX

Explanations

function definitions and function calls in programming code

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

uint followed by type qualifier

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

Slf

-0.35

queryInterface

-0.33

RTEE

-0.31

evos

-0.31

 descar

-0.31

XmlEnum

-0.30

 sociedades

-0.29

➟

-0.29

脚注の使い方

-0.29

-0.28

POSITIVE LOGITS

Externé

0.54

exitRule

0.53

requestCode

0.50

UnusedPrivate

0.50

HtmlAttribute

0.49

rrggbb

0.48

dhury

0.48

 ſeinem

0.48

ſelben

0.47

bora

0.47

Activations Density 0.085%

function definitions and function calls in programming code

uint followed by type qualifier

No Comments

No Known Activations