INDEX

Explanations

phrases indicating desires or intentions

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

 themselves

-0.92

="@+

-0.71

กัน

-0.68

CloseOperation

-0.65

 utafitiHapana

-0.65

themselves

-0.65

 their

-0.62

 Lordships

-0.60

 själva

-0.60

 bedoeld

-0.60

POSITIVE LOGITS

 myself

1.85

myself

1.51

 Myself

1.37

my

1.15

 myſelf

1.00

我自己

0.97

 خودم

0.96

 personally

0.95

Myself

0.94

my

0.90

Activations Density 1.195%

phrases indicating desires or intentions

No Comments

No Known Activations