INDEX

Explanations

references to specific document-related objects and functions in programming

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

files, time, and math libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

tvguidetime

-0.83

脚注の使い方

-0.68

 wireType

-0.60

AddTagHelper

-0.59

tangentMode

-0.59

printStackTrace

-0.59

 فريبيس

-0.58

 Italijanski

-0.58

 صوتيه

-0.55

RotationOrder

-0.53

POSITIVE LOGITS

 pathlib

0.61

gdx

0.57

 sympy

0.53

joda

0.52

 SwiftUI

0.49

jooq

0.49

 BeautifulSoup

0.47

QString

0.46

нор

0.43

LocalDate

0.39

Activations Density 0.198%

references to specific document-related objects and functions in programming

files, time, and math libraries

No Comments

No Known Activations