INDEX

Explanations

terms and concepts related to features and feature selection in data processing or data analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 photolibrary

-0.99

PVA

-0.94

 myſelf

-0.94

 pregunto

-0.93

 kantoor

-0.92

 nôtre

-0.91

 clearColor

-0.90

 Ankunft

-0.90

]^{-

-0.89

 pessoais

-0.88

POSITIVE LOGITS

 features

2.46

 feature

2.38

 Features

2.16

features

2.07

 Feature

2.06

Features

2.06

Feature

2.02

feature

2.02

 FEATURE

1.99

 FEATURES

1.90

Activations Density 0.038%

terms and concepts related to features and feature selection in data processing or data analysis contexts

No Comments

No Known Activations