INDEX

Explanations

references to the word "Lat" and variations related to latitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

//

-0.71

олові

-0.66

 PropTypes

-0.59

GID

-0.56

Alike

-0.54

 CreateTagHelper

-0.54

tagext

-0.52

STRUCTION

-0.52

 billede

-0.51

balleur

-0.50

POSITIVE LOGITS

AutoresizingMask

0.83

Lat

0.76

stdc

0.63

 Latimer

0.62

Lat

0.59

LAT

0.57

IntoConstraints

0.57

lat

0.57

getLong

0.56

 Lath

0.56

Activations Density 0.081%

references to the word "Lat" and variations related to latitude

No Comments

No Known Activations