INDEX

Explanations

references to research centers and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

🏻‍♀️

-0.84

氓

-0.82

-0.81

 Hogarth

-0.80

hubarb

-0.79

 McKinnon

-0.73

,$_

-0.73

 Eilish

-0.72

potranspiration

-0.72

Photoshop

-0.72

POSITIVE LOGITS

 centers

1.44

 centres

1.34

 Centers

1.32

 Center

1.27

 Centre

1.26

 Centres

1.23

 center

1.23

 CENTER

1.19

 centre

1.19

center

1.14

Activations Density 0.044%

references to research centers and institutions

No Comments

No Known Activations