INDEX

Explanations

references to the word "my" or variations of it within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 itſelf

-1.07

bbene

-0.97

 raiſ

-0.94

InjectAttribute

-0.90

abstractmethod

-0.89

 Monfieur

-0.89

 vectorielles

-0.87

 vectorielle

-0.86

 Houſe

-0.84

Efq

-0.84

POSITIVE LOGITS

My

1.34

own

1.26

MY

1.18

My

1.13

my

1.10

my

1.02

HIS

1.02

MY

1.00

getMy

0.98

Her

0.93

Activations Density 0.079%

references to the word "my" or variations of it within the text

No Comments

No Known Activations