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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Anſ

-1.29

 pleaſure

-1.26

 Monfieur

-1.23

Efq

-1.21

 reaſon

-1.19

 raiſ

-1.18

 Theſe

-1.15

 Majefty

-1.14

 himſelf

-1.13

 themſelves

-1.12

POSITIVE LOGITS

 Port

2.33

 port

2.24

port

2.13

Port

2.13

 PORT

2.06

PORT

1.94

 Ports

1.88

 ports

1.87

Ports

1.69

ports

1.57

Activations Density 0.042%

references to network ports

No Comments

No Known Activations