INDEX

Explanations

references to parameters in code documentation

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

Function parameter documentation

np_acts-logits-general · gemini-2.0-flash

documentation parameter names

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

IntoConstraints

-0.47

stdc

-0.46

 AspNetCore

-0.40

了过来

-0.39

 itſelf

-0.38

SaveChangesAsync

-0.37

contentLoaded

-0.37

 myſelf

-0.37

 âmes

-0.36

irq

-0.36

POSITIVE LOGITS

param

0.87

hdashline

0.53

ivar

0.52

 param

0.51

togram

0.51

 Param

0.49

脚注の使い方

0.48

ArgsConstructor

0.47

Trama

0.47

HasIndex

0.47

Activations Density 0.037%

references to parameters in code documentation

Function parameter documentation

documentation parameter names

No Comments

No Known Activations