INDEX

Explanations

references to specific locations and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Zhejiang

-0.61

httphttps

-0.59

 Marathi

-0.59

 Johor

-0.59

 Jalisco

-0.58

devtool

-0.58

findpost

-0.56

 Catt

-0.55

astify

-0.55

 Durban

-0.54

POSITIVE LOGITS

 Washington

1.71

DC

1.64

Washington

1.56

DC

1.44

 washington

1.32

 WASHINGTON

1.27

 Potomac

1.25

washington

1.21

 Capitals

1.18

dc

1.17

Activations Density 0.317%

references to specific locations and events

No Comments

No Known Activations