INDEX

Explanations

method calls related to adding components or elements in a programming context

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

Adding nodes or layers

np_acts-logits-general · gemini-2.0-flash

adding children to a parent

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

parsedMessage

-0.61

denly

-0.55

gameserver

-0.54

 NSCoder

-0.51

 متحده

-0.51

 poffible

-0.50

脚注の使い方

-0.50

ArrowToggle

-0.50

 queſta

-0.50

monie

-0.49

POSITIVE LOGITS

 CreateTagHelper

0.59

 addSubview

0.59

IContainer

0.51

arraycopy

0.47

addSubview

0.47

 inclui

0.45

حياته

0.45

'][]

0.45

 Include

0.44

addChild

0.43

Activations Density 0.193%

method calls related to adding components or elements in a programming context

Adding nodes or layers

adding children to a parent

No Comments

No Known Activations