INDEX

Explanations

references to work and its various forms, including related actions and roles

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Datuak

-0.99

 Nadel

-0.91

paravant

-0.86

 GIPHY

-0.85

 Apothe

-0.83

 Theſe

-0.82

AutoresizingMask

-0.82

 ſever

-0.82

 myſelf

-0.78

 Inhabitants

-0.77

POSITIVE LOGITS

 work

2.48

work

2.27

Work

2.23

 Work

2.21

 WORK

2.08

WORK

1.90

 works

1.86

works

1.64

 Works

1.60

Works

1.56

Activations Density 0.086%

references to work and its various forms, including related actions and roles

No Comments

No Known Activations