INDEX

Explanations

programmatic terminology related to implementation and properties in code structures

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

user input

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

centiles

-0.41

 Normdatei

-0.37

 atoi

-0.37

ieson

-0.36

 Alter

-0.35

Tazama

-0.35

ⓧ

-0.34

 tục

-0.34

 alts

-0.34

 squared

-0.33

POSITIVE LOGITS

 betweenstory

0.57

IntoConstraints

0.57

+#+

0.56

RenderAtEndOf

0.54

 AssemblyCompany

0.51

منابع

0.50

operator

0.50

 operator

0.49

出版年

0.46

UnknownFieldSet

0.44

Activations Density 0.024%

programmatic terminology related to implementation and properties in code structures

user input

No Comments

No Known Activations