INDEX

Explanations

references to personal relationships or family members

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 itſelf

-1.25

 themſelves

-1.03

 Theſe

-1.02

 Reſ

-1.00

 Houſe

-0.99

 Monfieur

-0.94

 Beſ

-0.94

 Anſ

-0.93

 himſelf

-0.92

Efq

-0.90

POSITIVE LOGITS

my

1.52

My

1.44

my

1.27

My

1.24

1.13

MY

1.11

getMy

1.07

Me

0.98

我的

0.95

 我的

0.94

Activations Density 0.059%

references to personal relationships or family members

No Comments

No Known Activations