INDEX

Explanations

references to layout-related terms in a coding context, particularly those related to column structures

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

 المعيارى

-1.02

setupUi

-0.98

évaluateur

-0.92

 صوتيه

-0.87

InjectAttribute

-0.86

цездатний

-0.85

WithIOException

-0.81

IUrlHelper

-0.80

 Catawiki

-0.78

ьаж

-0.77

POSITIVE LOGITS

col

2.41

COL

1.14

col

1.13

Col

1.11

cols

1.03

 column

0.90

 coluna

0.87

Column

0.81

column

0.81

Col

0.79

Activations Density 0.041%

references to layout-related terms in a coding context, particularly those related to column structures

No Comments

No Known Activations