INDEX

Explanations

references to ports and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 raiſ

-1.33

 pleaſure

-1.33

 myſelf

-1.26

 himſelf

-1.19

 uſed

-1.18

Efq

-1.17

 Anſ

-1.16

 reaſon

-1.14

 faſt

-1.13

 Monfieur

-1.12

POSITIVE LOGITS

 Port

3.70

 port

3.66

Port

3.42

port

3.07

 PORT

2.88

 ports

2.80

 Ports

2.70

PORT

2.67

Ports

2.24

ポート

2.19

Activations Density 0.033%

references to ports and related terminology

No Comments

No Known Activations