INDEX

Explanations

references to programming and debugging-related issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

Wrk

-0.45

vif

-0.41

kolwiek

-0.39

 کت

-0.38

くれます

-0.36

 interessanti

-0.36

PIB

-0.34

 nenhum

-0.33

还要

-0.33

 Herald

-0.33

POSITIVE LOGITS

 AssemblyCulture

1.14

 estimés

1.13

GEBURTSDATUM

0.92

uxxxx

0.87

 때문

0.87

ViewFeatures

0.87

afficheront

0.86

 disambiguazione

0.85

enumi

0.84

UserScript

0.81

Activations Density 0.516%

references to programming and debugging-related issues

No Comments

No Known Activations