INDEX

Explanations

references to specific names or entities, particularly those related to individuals and their works

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

Tokens preceding a person's last name

np_acts-logits-general · gemini-2.0-flash

name followed by surname or identifier

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

tagHelperRunner

-0.60

 visst

-0.58

GIVEREF

-0.57

ية

-0.55

 helst

-0.54

туаль

-0.53

 elif

-0.53

sno

-0.50

addContainerGap

-0.49

يتها

-0.49

POSITIVE LOGITS

jspx

0.73

elten

0.73

GEBURTSDATUM

0.73

]();

0.73

WriteTagHelper

0.71

்கள்

0.66

WTS

0.65

ForKey

0.65

 dentaire

0.64

Sucesor

0.62

Activations Density 0.532%

references to specific names or entities, particularly those related to individuals and their works

Tokens preceding a person's last name

name followed by surname or identifier

No Comments

No Known Activations