INDEX

Explanations

mentions of the word "au" in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

RenderAtEndOf

-0.95

Havolalar

-0.75

 abstrait

-0.74

 chiếu

-0.67

 Breeze

-0.63

 StringVar

-0.63

 optique

-0.63

 lisse

-0.61

 communautaire

-0.61

 mécanisme

-0.60

POSITIVE LOGITS

au

3.15

au

3.12

Au

3.02

Au

2.87

AU

2.35

AU

2.29

AUD

1.37

AUD

1.34

 Auro

1.25

auk

1.25

Activations Density 0.026%

mentions of the word "au" in varying contexts

No Comments

No Known Activations