INDEX

Explanations

processes related to cleaning

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

CAREER

-0.66

 AssemblyCulture

-0.66

odeficiency

-0.66

-0.65

azgo

-0.64

 Egli

-0.63

الإنجليزية

-0.63

 cương

-0.62

 espagne

-0.62

 Вікіпе

-0.61

POSITIVE LOGITS

 wash

2.32

 washing

2.22

 washed

2.12

 washes

2.09

Wash

2.04

 Wash

2.00

wash

2.00

 WASH

1.97

washing

1.96

 Washing

1.86

Activations Density 0.049%

processes related to cleaning

No Comments

No Known Activations