INDEX

Explanations

terms related to spatial aspects 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 @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.61

-0.56

er

-0.56

gar

-0.55

 Warsaw

-0.53

Joc

-0.53

BMS

-0.52

ウェイ

-0.52

 colegio

-0.51

 Comprometido

-0.50

POSITIVE LOGITS

 spatial

2.63

spatial

2.47

 Spatial

2.47

Spatial

2.36

 spatially

1.99

temporal

1.68

 spatio

1.62

 temporal

1.59

 spati

1.51

Temporal

1.50

Activations Density 0.142%

terms related to spatial aspects in various contexts

No Comments

No Known Activations