INDEX

Explanations

references to geometric points and coordinate systems in a computational context

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

 صوتيه

-0.78

checkable

-0.72

 saites

-0.68

 linkovi

-0.67

 COMPOUNDS

-0.66

()]);

-0.64

 JpaRepository

-0.63

ErrorListener

-0.61

 AssemblyCulture

-0.61

 APPARATUS

-0.59

POSITIVE LOGITS

Point

2.67

 Point

2.24

POINT

1.73

point

1.69

 POINT

1.64

 point

1.63

 Points

1.37

Points

1.32

points

1.26

 points

1.25

Activations Density 0.061%

references to geometric points and coordinate systems in a computational context

No Comments

No Known Activations