INDEX

Explanations

words and phrases related to improvement and enhancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PathVariable

-0.66

 HasFactory

-0.62

ne

-0.62

Koz

-0.59

Kos

-0.58

yl

-0.55

-0.54

 Sass

-0.54

 listrik

-0.54

 cadeia

-0.54

POSITIVE LOGITS

 Improvements

1.26

esserung

1.25

 improvement

1.23

 Improvement

1.22

 IMPRO

1.21

Improvements

1.18

 myſelf

1.17

 Improves

1.17

 improvements

1.17

Improve

1.15

Activations Density 0.089%

words and phrases related to improvement and enhancement

No Comments

No Known Activations