INDEX

Explanations

mentions of contributions or contributions made in various contexts

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

 etern

-0.59

 compter

-0.52

epam

-0.52

WebElementEntity

-0.52

 Normdatei

-0.50

 pronon

-0.50

 deten

-0.49

webElementXpaths

-0.49

行き

-0.49

 Sorg

-0.49

POSITIVE LOGITS

 qualifications

1.07

 qualification

1.03

 credentials

0.99

 Credentials

0.98

 Qualification

0.90

qualification

0.84

 Qualifications

0.84

credentials

0.83

onAttach

0.80

 Contribution

0.78

Activations Density 0.076%

mentions of contributions or contributions made in various contexts

No Comments

No Known Activations