INDEX

Explanations

the word "your" and its variations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

InjectAttribute

-1.08

 Normdatei

-1.04

Personensuche

-1.03

 himself

-1.02

DockStyle

-0.96

 Himself

-0.95

himself

-0.93

awtextra

-0.87

IndentedString

-0.79

AddAttribute

-0.79

POSITIVE LOGITS

 your

1.47

your

1.30

 Your

1.21

YOUR

1.21

 YOUR

1.20

Your

1.16

our

1.13

 votre

1.12

own

1.09

 vostro

1.05

Activations Density 0.075%

the word "your" and its variations in text

No Comments

No Known Activations