INDEX

Explanations

references to network ports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

-0.94

 myſelf

-0.92

 Monfieur

-0.91

 pleaſure

-0.89

 Majefty

-0.88

 automatiques

-0.88

 Houſe

-0.88

Efq

-0.87

 doubtnut

-0.87

存于互联网档案馆

-0.85

POSITIVE LOGITS

 port

4.16

port

4.05

 Port

3.96

Port

3.90

PORT

3.60

 PORT

3.43

 ports

3.03

ports

2.69

 Ports

2.66

ポート

2.50

Activations Density 0.048%

references to network ports

No Comments

No Known Activations