INDEX

Explanations

phrases indicating personal connections or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

GOTREF

-0.62

 initComponents

-0.52

 inconnu

-0.48

softc

-0.48

RectangleBorder

-0.47

WriteLiteral

-0.47

RTEE

-0.47

 становника

-0.46

 estimés

-0.44

POSITIVE LOGITS

 covered

1.54

covered

1.26

 Covered

1.25

Covered

1.22

 COVER

1.01

 cubierto

0.99

 bases

0.95

 cover

0.92

cov

0.90

 coverage

0.89

Activations Density 0.087%

phrases indicating personal connections or relationships

No Comments

No Known Activations